Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4435 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.6601. Min Act: -0.1700
Data Index: 5544236 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.5976. Min Act: -0.1700
Data Index: 1767607 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.5664. Min Act: -0.1700
Data Index: 5232761 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.5976. Min Act: -0.1700
Data Index: 5958681 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.5351. Min Act: -0.1700
Data Index: 5342491 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.5039. Min Act: -0.1700
Data Index: 1257257 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.5039. Min Act: -0.1700
Data Index: 6309073 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.5039. Min Act: -0.1700
Data Index: 4401393 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.5039. Min Act: -0.1700
Data Index: 8780567 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.4726. Min Act: -0.1700
Data Index: 1361248 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.4726. Min Act: -0.1700
Data Index: 5758106 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.4101. Min Act: -0.1700
Data Index: 954130 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.4101. Min Act: -0.1700
Data Index: 2020060 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.3789. Min Act: -0.1700
Data Index: 3836525 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.3476. Min Act: -0.1700
Data Index: 1264368 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.3789. Min Act: -0.1700
Data Index: 1961606 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.3789. Min Act: -0.1700
Data Index: 807728 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.3789. Min Act: -0.1700
Data Index: 3540857 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.3789. Min Act: -0.1700
Data Index: 7973595 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6601. Min Range: -6.6601
Max Act: 6.3789. Min Act: -0.1700
Data Index: 1253485 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19