Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.5777. Min Act: -0.1700
Data Index: 3675833 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.5152. Min Act: -0.1700
Data Index: 2795640 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.4527. Min Act: -0.1700
Data Index: 486290 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.4214. Min Act: -0.1700
Data Index: 4032687 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.3902. Min Act: -0.1700
Data Index: 4700918 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.3902. Min Act: -0.1700
Data Index: 8795630 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.3589. Min Act: -0.1700
Data Index: 8082342 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.3277. Min Act: -0.1700
Data Index: 4515838 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.3277. Min Act: -0.1700
Data Index: 929324 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.3277. Min Act: -0.1700
Data Index: 6229573 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.3589. Min Act: -0.1700
Data Index: 2494875 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.3277. Min Act: -0.1700
Data Index: 3811510 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.2964. Min Act: -0.1700
Data Index: 7156969 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.2964. Min Act: -0.1700
Data Index: 6753302 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.2652. Min Act: -0.1700
Data Index: 8795623 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.2652. Min Act: -0.1700
Data Index: 7156970 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.2339. Min Act: -0.1700
Data Index: 5538271 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.2652. Min Act: -0.1700
Data Index: 5070950 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.2652. Min Act: -0.1700
Data Index: 5781466 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5777. Min Range: -6.5777
Max Act: 6.2339. Min Act: -0.1700
Data Index: 2862049 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19