Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1957 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.1341. Min Act: -0.1700
Data Index: 5459371 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.1026. Min Act: -0.1700
Data Index: 4724504 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.1026. Min Act: -0.1700
Data Index: 563455 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0868. Min Act: -0.1700
Data Index: 5446242 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0868. Min Act: -0.1700
Data Index: 4829048 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0868. Min Act: -0.1700
Data Index: 7802715 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0710. Min Act: -0.1700
Data Index: 6454006 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0552. Min Act: -0.1700
Data Index: 8394104 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0552. Min Act: -0.1700
Data Index: 3617959 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0552. Min Act: -0.1700
Data Index: 7583870 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0552. Min Act: -0.1700
Data Index: 4195000 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0552. Min Act: -0.1700
Data Index: 7857381 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0552. Min Act: -0.1700
Data Index: 3167957 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0395. Min Act: -0.1700
Data Index: 2700253 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0395. Min Act: -0.1700
Data Index: 6378593 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0395. Min Act: -0.1700
Data Index: 6088687 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0395. Min Act: -0.1700
Data Index: 779198 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0395. Min Act: -0.1700
Data Index: 6812939 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0395. Min Act: -0.1700
Data Index: 3257127 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1341. Min Range: -3.1341
Max Act: 3.0237. Min Act: -0.1700
Data Index: 4860950 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19