Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3806 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.7289. Min Act: -0.1700
Data Index: 7233987 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.6664. Min Act: -0.1700
Data Index: 7876885 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.6039. Min Act: -0.1700
Data Index: 4806447 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.5102. Min Act: -0.1700
Data Index: 4774240 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.5102. Min Act: -0.1700
Data Index: 8522130 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.4789. Min Act: -0.1700
Data Index: 5446388 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.4789. Min Act: -0.1700
Data Index: 5865852 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.4789. Min Act: -0.1700
Data Index: 166096 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.4789. Min Act: -0.1700
Data Index: 3563480 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.4164. Min Act: -0.1700
Data Index: 3851120 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.4164. Min Act: -0.1700
Data Index: 837693 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.4164. Min Act: -0.1700
Data Index: 4996967 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.3852. Min Act: -0.1700
Data Index: 7946008 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.3227. Min Act: -0.1700
Data Index: 3290446 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.3539. Min Act: -0.1700
Data Index: 5258569 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.3227. Min Act: -0.1700
Data Index: 3208683 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.3539. Min Act: -0.1700
Data Index: 7509358 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.3227. Min Act: -0.1700
Data Index: 5915066 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.2914. Min Act: -0.1700
Data Index: 4325874 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7289. Min Range: -5.7289
Max Act: 5.2914. Min Act: -0.1700
Data Index: 738564 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19