Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2896 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.9270. Min Act: -0.1700
Data Index: 7746915 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.9270. Min Act: -0.1700
Data Index: 8806667 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.8332. Min Act: -0.1700
Data Index: 5700394 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.8020. Min Act: -0.1700
Data Index: 6125455 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.8020. Min Act: -0.1700
Data Index: 5206605 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.7707. Min Act: -0.1700
Data Index: 6962065 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.7395. Min Act: -0.1700
Data Index: 3478228 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.7395. Min Act: -0.1700
Data Index: 7013902 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.7395. Min Act: -0.1700
Data Index: 8465536 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.7082. Min Act: -0.1700
Data Index: 4623787 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.6770. Min Act: -0.1700
Data Index: 7005180 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.7082. Min Act: -0.1700
Data Index: 1400415 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.6770. Min Act: -0.1700
Data Index: 1345696 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.7082. Min Act: -0.1700
Data Index: 5337707 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.7395. Min Act: -0.1700
Data Index: 69890 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.7082. Min Act: -0.1700
Data Index: 5127974 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.7082. Min Act: -0.1700
Data Index: 7491253 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.6770. Min Act: -0.1700
Data Index: 315660 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.6457. Min Act: -0.1700
Data Index: 6330420 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9270. Min Range: -4.9270
Max Act: 4.6770. Min Act: -0.1700
Data Index: 6487887 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19