Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.7130. Min Act: -0.1700
Data Index: 8187212 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.5568. Min Act: -0.1700
Data Index: 1439373 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.4005. Min Act: -0.1700
Data Index: 8318986 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.3693. Min Act: -0.1700
Data Index: 2871408 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.3068. Min Act: -0.1700
Data Index: 1554635 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.2755. Min Act: -0.1700
Data Index: 120666 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.2443. Min Act: -0.1700
Data Index: 5596975 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.2443. Min Act: -0.1700
Data Index: 6545795 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.1818. Min Act: -0.1700
Data Index: 4810793 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.1818. Min Act: -0.1700
Data Index: 8109519 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.1818. Min Act: -0.1700
Data Index: 1876561 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.1505. Min Act: -0.1700
Data Index: 149038 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.1193. Min Act: -0.1700
Data Index: 5493319 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.0880. Min Act: -0.1700
Data Index: 601483 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.0568. Min Act: -0.1700
Data Index: 4877763 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7130. Min Range: -7.7130
Max Act: 6.9943. Min Act: -0.1700
Data Index: 6074008 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7130. Min Range: -7.7130
Max Act: 7.0255. Min Act: -0.1700
Data Index: 3982620 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7130. Min Range: -7.7130
Max Act: 6.9943. Min Act: -0.1700
Data Index: 8224428 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7130. Min Range: -7.7130
Max Act: 6.9630. Min Act: -0.1700
Data Index: 8274836 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7130. Min Range: -7.7130
Max Act: 6.9630. Min Act: -0.1700
Data Index: 1269271 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19