Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2723 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.8122. Min Act: -0.1700
Data Index: 3589801 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.7497. Min Act: -0.1700
Data Index: 4182046 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.7497. Min Act: -0.1700
Data Index: 3131966 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.7497. Min Act: -0.1700
Data Index: 8473004 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6872. Min Act: -0.1700
Data Index: 462682 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.7185. Min Act: -0.1700
Data Index: 8473003 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.7185. Min Act: -0.1700
Data Index: 6916811 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6872. Min Act: -0.1700
Data Index: 7769418 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6872. Min Act: -0.1700
Data Index: 7483592 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6560. Min Act: -0.1700
Data Index: 8454187 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6560. Min Act: -0.1700
Data Index: 1463234 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6560. Min Act: -0.1700
Data Index: 4750135 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6560. Min Act: -0.1700
Data Index: 5750411 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6560. Min Act: -0.1700
Data Index: 7435079 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6560. Min Act: -0.1700
Data Index: 3672567 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6560. Min Act: -0.1700
Data Index: 1181894 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6247. Min Act: -0.1700
Data Index: 3359995 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6247. Min Act: -0.1700
Data Index: 3771816 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6247. Min Act: -0.1700
Data Index: 6276140 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8122. Min Range: -5.8122
Max Act: 5.6247. Min Act: -0.1700
Data Index: 4126269 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19