Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5130 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.3811. Min Act: -0.1700
Data Index: 2857980 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.3654. Min Act: -0.1700
Data Index: 7867493 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.3497. Min Act: -0.1700
Data Index: 594365 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.3340. Min Act: -0.1700
Data Index: 5100038 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.3183. Min Act: -0.1700
Data Index: 7692213 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.3183. Min Act: -0.1700
Data Index: 541214 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.3183. Min Act: -0.1700
Data Index: 2917306 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.3026. Min Act: -0.1700
Data Index: 6155094 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.3026. Min Act: -0.1700
Data Index: 3802326 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.3026. Min Act: -0.1700
Data Index: 8684538 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.2869. Min Act: -0.1700
Data Index: 5629640 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.2869. Min Act: -0.1700
Data Index: 6338814 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.2712. Min Act: -0.1700
Data Index: 7093308 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.2712. Min Act: -0.1700
Data Index: 7175706 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.2712. Min Act: -0.1700
Data Index: 7729087 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.2712. Min Act: -0.1700
Data Index: 5680502 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.2869. Min Act: -0.1700
Data Index: 3663973 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.2555. Min Act: -0.1700
Data Index: 6881670 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.2555. Min Act: -0.1700
Data Index: 511221 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3811. Min Range: -3.3811
Max Act: 3.2398. Min Act: -0.1700
Data Index: 5293747 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19