Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4081 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1204. Min Range: -6.1204
Max Act: 6.1204. Min Act: -0.1700
Data Index: 140257 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1204. Min Range: -6.1204
Max Act: 6.1204. Min Act: -0.1700
Data Index: 6669620 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1204. Min Range: -6.1204
Max Act: 6.0579. Min Act: -0.1700
Data Index: 3435719 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1204. Min Range: -6.1204
Max Act: 6.0267. Min Act: -0.1700
Data Index: 5021212 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.9954. Min Act: -0.1700
Data Index: 3086 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.9329. Min Act: -0.1700
Data Index: 7568972 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.9017. Min Act: -0.1700
Data Index: 7647173 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.9017. Min Act: -0.1700
Data Index: 3872317 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.8704. Min Act: -0.1700
Data Index: 5438558 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.8392. Min Act: -0.1700
Data Index: 4154531 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.8392. Min Act: -0.1700
Data Index: 5855814 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.8079. Min Act: -0.1700
Data Index: 4245031 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.8079. Min Act: -0.1700
Data Index: 8793464 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.8079. Min Act: -0.1700
Data Index: 1672324 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.8079. Min Act: -0.1700
Data Index: 4115378 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.7767. Min Act: -0.1700
Data Index: 8153539 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.7767. Min Act: -0.1700
Data Index: 7495889 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.7767. Min Act: -0.1700
Data Index: 693111 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.7767. Min Act: -0.1700
Data Index: 5542342 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1204. Min Range: -6.1204
Max Act: 5.7454. Min Act: -0.1700
Data Index: 5492622 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19