Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2544 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.5791. Min Act: -0.1700
Data Index: 1641131 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.5166. Min Act: -0.1700
Data Index: 1617609 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.4541. Min Act: -0.1700
Data Index: 755121 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.4229. Min Act: -0.1700
Data Index: 4739716 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.4541. Min Act: -0.1700
Data Index: 8610967 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.4541. Min Act: -0.1700
Data Index: 6703573 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.4229. Min Act: -0.1700
Data Index: 7757415 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.3604. Min Act: -0.1700
Data Index: 1995374 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.3604. Min Act: -0.1700
Data Index: 1627718 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.3604. Min Act: -0.1700
Data Index: 2485362 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.3291. Min Act: -0.1700
Data Index: 6884109 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.3604. Min Act: -0.1700
Data Index: 8507500 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.3291. Min Act: -0.1700
Data Index: 3422845 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.3291. Min Act: -0.1700
Data Index: 6690889 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.2979. Min Act: -0.1700
Data Index: 7922816 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.2666. Min Act: -0.1700
Data Index: 1790910 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.2666. Min Act: -0.1700
Data Index: 4388950 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.2666. Min Act: -0.1700
Data Index: 2662950 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.2666. Min Act: -0.1700
Data Index: 7062039 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5791. Min Range: -7.5791
Max Act: 7.2354. Min Act: -0.1700
Data Index: 4755336 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19