Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 397 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.7149. Min Act: -0.1700
Data Index: 8302933 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.5898. Min Act: -0.1700
Data Index: 6235956 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.5271. Min Act: -0.1700
Data Index: 5100866 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.5428. Min Act: -0.1700
Data Index: 2238270 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.5271. Min Act: -0.1700
Data Index: 8658646 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.5271. Min Act: -0.1700
Data Index: 5137484 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.4958. Min Act: -0.1700
Data Index: 882702 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.5271. Min Act: -0.1700
Data Index: 2728416 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.4958. Min Act: -0.1700
Data Index: 1324547 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.4958. Min Act: -0.1700
Data Index: 6400731 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.4958. Min Act: -0.1700
Data Index: 4786650 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.4801. Min Act: -0.1700
Data Index: 5964191 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.4801. Min Act: -0.1700
Data Index: 4481374 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.4801. Min Act: -0.1700
Data Index: 3344285 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.4645. Min Act: -0.1700
Data Index: 2634377 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.4645. Min Act: -0.1700
Data Index: 5110159 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.4645. Min Act: -0.1700
Data Index: 572004 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.4645. Min Act: -0.1700
Data Index: 7334516 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.4488. Min Act: -0.1700
Data Index: 8031729 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7149. Min Range: -3.7149
Max Act: 3.4488. Min Act: -0.1700
Data Index: 3327376 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19