Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2433 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3791. Min Act: -0.1700
Data Index: 5526803 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3791. Min Act: -0.1700
Data Index: 6469277 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3478. Min Act: -0.1700
Data Index: 4552537 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3634. Min Act: -0.1700
Data Index: 6870599 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3321. Min Act: -0.1700
Data Index: 5080220 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3321. Min Act: -0.1700
Data Index: 1053333 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3321. Min Act: -0.1700
Data Index: 5776744 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3164. Min Act: -0.1700
Data Index: 8661937 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3164. Min Act: -0.1700
Data Index: 4497990 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3007. Min Act: -0.1700
Data Index: 8730400 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.2850. Min Act: -0.1700
Data Index: 1899557 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3007. Min Act: -0.1700
Data Index: 8498766 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3007. Min Act: -0.1700
Data Index: 3341498 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3007. Min Act: -0.1700
Data Index: 3676868 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3007. Min Act: -0.1700
Data Index: 5707921 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3007. Min Act: -0.1700
Data Index: 4176264 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3007. Min Act: -0.1700
Data Index: 1460499 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.3007. Min Act: -0.1700
Data Index: 2025000 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.2850. Min Act: -0.1700
Data Index: 3164219 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3791. Min Range: -3.3791
Max Act: 3.2850. Min Act: -0.1700
Data Index: 2681787 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19