Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2798 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9681. Min Act: -0.1700
Data Index: 3349095 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9368. Min Act: -0.1700
Data Index: 1563203 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9368. Min Act: -0.1700
Data Index: 8539670 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9368. Min Act: -0.1700
Data Index: 8575249 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9055. Min Act: -0.1700
Data Index: 52733 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9055. Min Act: -0.1700
Data Index: 6888279 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9055. Min Act: -0.1700
Data Index: 317385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9055. Min Act: -0.1700
Data Index: 3339858 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9055. Min Act: -0.1700
Data Index: 1832482 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9055. Min Act: -0.1700
Data Index: 3669014 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8743. Min Act: -0.1700
Data Index: 6045826 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8743. Min Act: -0.1700
Data Index: 5817056 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8743. Min Act: -0.1700
Data Index: 4375845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8743. Min Act: -0.1700
Data Index: 2293788 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8743. Min Act: -0.1700
Data Index: 4285969 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8743. Min Act: -0.1700
Data Index: 8373327 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8743. Min Act: -0.1700
Data Index: 6372441 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8430. Min Act: -0.1700
Data Index: 5090206 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8430. Min Act: -0.1700
Data Index: 5768067 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8430. Min Act: -0.1700
Data Index: 5782427 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19