Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3499 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2193. Min Range: -9.2193
Max Act: 9.2193. Min Act: -0.1700
Data Index: 1201804 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.5943. Min Act: -0.1700
Data Index: 2844699 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.3443. Min Act: -0.1700
Data Index: 5656685 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.3443. Min Act: -0.1700
Data Index: 403237 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.2818. Min Act: -0.1700
Data Index: 8131702 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.2818. Min Act: -0.1700
Data Index: 4038099 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.1568. Min Act: -0.1700
Data Index: 6315912 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.2193. Min Act: -0.1700
Data Index: 4898100 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.1568. Min Act: -0.1700
Data Index: 5523242 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.2193. Min Act: -0.1700
Data Index: 496389 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.1568. Min Act: -0.1700
Data Index: 2355698 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.2193. Min Act: -0.1700
Data Index: 974842 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.0943. Min Act: -0.1700
Data Index: 949327 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.0943. Min Act: -0.1700
Data Index: 6381207 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.0943. Min Act: -0.1700
Data Index: 40045 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.0943. Min Act: -0.1700
Data Index: 2388162 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.0943. Min Act: -0.1700
Data Index: 7941993 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.0318. Min Act: -0.1700
Data Index: 4934096 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.0318. Min Act: -0.1700
Data Index: 2873693 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2193. Min Range: -9.2193
Max Act: 8.0318. Min Act: -0.1700
Data Index: 2678669 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19