Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.5989. Min Range: -13.5989
Max Act: 13.5989. Min Act: -0.1700
Data Index: 1021479 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.5989. Min Range: -13.5989
Max Act: 13.1614. Min Act: -0.1700
Data Index: 1021477 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.5364. Min Act: -0.1700
Data Index: 8715213 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.4739. Min Act: -0.1700
Data Index: 1021476 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.4739. Min Act: -0.1700
Data Index: 1540037 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.4114. Min Act: -0.1699
Data Index: 5033328 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.4114. Min Act: -0.1700
Data Index: 1021463 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.3489. Min Act: -0.1700
Data Index: 4560105 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.3489. Min Act: -0.1700
Data Index: 824210 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.2239. Min Act: -0.1700
Data Index: 7683164 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.2239. Min Act: -0.1700
Data Index: 1021487 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.1614. Min Act: -0.1700
Data Index: 3720732 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.1614. Min Act: -0.1700
Data Index: 3871390 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.1614. Min Act: -0.1700
Data Index: 4434908 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.0364. Min Act: -0.1700
Data Index: 4487922 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.0989. Min Act: -0.1700
Data Index: 6238920 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.0364. Min Act: -0.1700
Data Index: 591905 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.5989. Min Range: -13.5989
Max Act: 11.9739. Min Act: -0.1700
Data Index: 1554648 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.5989. Min Range: -13.5989
Max Act: 11.9739. Min Act: -0.1700
Data Index: 4873042 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.5989. Min Range: -13.5989
Max Act: 12.0364. Min Act: -0.1700
Data Index: 7219061 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19