Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3978 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.6380. Min Act: -0.1700
Data Index: 5208130 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.6067. Min Act: -0.1700
Data Index: 8602556 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.5442. Min Act: -0.1700
Data Index: 5208131 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.5130. Min Act: -0.1700
Data Index: 332955 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.4817. Min Act: -0.1700
Data Index: 4053702 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.3880. Min Act: -0.1700
Data Index: 8750067 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.3567. Min Act: -0.1700
Data Index: 7101798 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.3255. Min Act: -0.1700
Data Index: 6407171 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.3255. Min Act: -0.1700
Data Index: 785496 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.3255. Min Act: -0.1700
Data Index: 3200706 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.3255. Min Act: -0.1700
Data Index: 2652427 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.3255. Min Act: -0.1700
Data Index: 3629097 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.2942. Min Act: -0.1700
Data Index: 3746091 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.3255. Min Act: -0.1700
Data Index: 7465040 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.2317. Min Act: -0.1700
Data Index: 6370171 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.2317. Min Act: -0.1700
Data Index: 6446338 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.2317. Min Act: -0.1700
Data Index: 165433 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.2317. Min Act: -0.1700
Data Index: 6945423 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.2317. Min Act: -0.1700
Data Index: 6049995 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6380. Min Range: -5.6380
Max Act: 5.2317. Min Act: -0.1700
Data Index: 4890784 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19