Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 317 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.7100. Min Act: -0.1700
Data Index: 8614130 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.5538. Min Act: -0.1700
Data Index: 6295503 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.3663. Min Act: -0.1700
Data Index: 516280 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.3663. Min Act: -0.1700
Data Index: 6844579 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.3350. Min Act: -0.1700
Data Index: 3166015 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.3350. Min Act: -0.1700
Data Index: 4626448 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.2725. Min Act: -0.1700
Data Index: 5836747 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.2413. Min Act: -0.1700
Data Index: 8255642 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.2100. Min Act: -0.1700
Data Index: 8742947 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.2100. Min Act: -0.1700
Data Index: 1595931 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.1788. Min Act: -0.1700
Data Index: 8676800 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.1788. Min Act: -0.1700
Data Index: 3255310 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.1163. Min Act: -0.1700
Data Index: 7991878 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.1163. Min Act: -0.1700
Data Index: 6180015 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.1163. Min Act: -0.1700
Data Index: 8204715 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.0850. Min Act: -0.1700
Data Index: 1319591 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.0850. Min Act: -0.1700
Data Index: 8325609 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.0538. Min Act: -0.1700
Data Index: 311348 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.0538. Min Act: -0.1700
Data Index: 8765720 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7100. Min Range: -5.7100
Max Act: 5.0538. Min Act: -0.1700
Data Index: 2807096 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19