Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2719 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5320. Min Range: -11.5320
Max Act: 11.5320. Min Act: -0.1700
Data Index: 1847392 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5320. Min Range: -11.5320
Max Act: 11.1570. Min Act: -0.1700
Data Index: 6543711 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.7195. Min Act: -0.1700
Data Index: 2387721 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.7195. Min Act: -0.1700
Data Index: 8031161 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.6570. Min Act: -0.1700
Data Index: 4517322 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.4695. Min Act: -0.1700
Data Index: 3803305 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.5320. Min Act: -0.1700
Data Index: 8040309 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.5320. Min Act: -0.1700
Data Index: 2052582 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.4695. Min Act: -0.1700
Data Index: 3620506 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.3445. Min Act: -0.1700
Data Index: 1222231 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.2820. Min Act: -0.1700
Data Index: 6110582 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.2820. Min Act: -0.1700
Data Index: 7889106 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.2820. Min Act: -0.1700
Data Index: 3171788 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.2195. Min Act: -0.1700
Data Index: 3553631 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.1570. Min Act: -0.1700
Data Index: 4489121 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.2195. Min Act: -0.1700
Data Index: 6083350 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.0945. Min Act: -0.1700
Data Index: 3471406 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.0945. Min Act: -0.1700
Data Index: 4113795 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.0320. Min Act: -0.1700
Data Index: 7837688 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5320. Min Range: -11.5320
Max Act: 10.0320. Min Act: -0.1700
Data Index: 8737987 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19