Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.4851. Min Act: -0.1700
Data Index: 2518150 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.4226. Min Act: -0.1700
Data Index: 6652376 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.3914. Min Act: -0.1700
Data Index: 1147392 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.3914. Min Act: -0.1700
Data Index: 3639819 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.3601. Min Act: -0.1700
Data Index: 6093288 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.3289. Min Act: -0.1700
Data Index: 8091652 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.2039. Min Act: -0.1700
Data Index: 2256649 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.1414. Min Act: -0.1700
Data Index: 434462 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.1414. Min Act: -0.1700
Data Index: 6757007 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.1101. Min Act: -0.1700
Data Index: 5146431 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.1101. Min Act: -0.1700
Data Index: 3274278 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.0789. Min Act: -0.1700
Data Index: 8726600 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.0476. Min Act: -0.1700
Data Index: 6517373 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.0476. Min Act: -0.1700
Data Index: 5421357 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.0476. Min Act: -0.1700
Data Index: 7513057 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.0164. Min Act: -0.1700
Data Index: 5704466 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.0164. Min Act: -0.1700
Data Index: 4951826 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4851. Min Range: -6.4851
Max Act: 5.9851. Min Act: -0.1700
Data Index: 5370149 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4851. Min Range: -6.4851
Max Act: 6.0164. Min Act: -0.1700
Data Index: 8562433 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4851. Min Range: -6.4851
Max Act: 5.9851. Min Act: -0.1700
Data Index: 2414989 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19