Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0183. Min Range: -6.0183
Max Act: 6.0183. Min Act: -0.1700
Data Index: 3133765 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0183. Min Range: -6.0183
Max Act: 6.0183. Min Act: -0.1700
Data Index: 3353086 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.9871. Min Act: -0.1700
Data Index: 4969623 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.8308. Min Act: -0.1700
Data Index: 4494415 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.7996. Min Act: -0.1700
Data Index: 7731954 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.7058. Min Act: -0.1700
Data Index: 6943264 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.7371. Min Act: -0.1700
Data Index: 2901434 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.7683. Min Act: -0.1700
Data Index: 817578 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.7371. Min Act: -0.1700
Data Index: 7467087 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.7371. Min Act: -0.1700
Data Index: 4731780 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.7058. Min Act: -0.1700
Data Index: 2244917 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.7058. Min Act: -0.1700
Data Index: 4175689 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.7058. Min Act: -0.1700
Data Index: 4602118 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.6433. Min Act: -0.1700
Data Index: 1854601 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.6433. Min Act: -0.1700
Data Index: 1988937 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.6121. Min Act: -0.1700
Data Index: 1443236 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.5808. Min Act: -0.1700
Data Index: 3654252 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.6121. Min Act: -0.1700
Data Index: 3690567 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.5808. Min Act: -0.1700
Data Index: 5236464 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0183. Min Range: -6.0183
Max Act: 5.5808. Min Act: -0.1700
Data Index: 4258711 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19