Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2991 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.6780. Min Act: -0.1700
Data Index: 791557 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.5217. Min Act: -0.1700
Data Index: 5981176 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.5530. Min Act: -0.1700
Data Index: 7463949 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.3655. Min Act: -0.1700
Data Index: 2441000 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.3342. Min Act: -0.1700
Data Index: 2575102 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.3030. Min Act: -0.1700
Data Index: 3457292 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.3030. Min Act: -0.1700
Data Index: 2067275 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.3030. Min Act: -0.1700
Data Index: 4582775 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.2404. Min Act: -0.1700
Data Index: 1027180 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.2404. Min Act: -0.1700
Data Index: 8251103 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.2404. Min Act: -0.1700
Data Index: 5635245 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.2092. Min Act: -0.1700
Data Index: 4139461 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.2092. Min Act: -0.1700
Data Index: 2492468 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.1779. Min Act: -0.1700
Data Index: 1673157 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.1779. Min Act: -0.1700
Data Index: 5499016 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.1779. Min Act: -0.1700
Data Index: 8111972 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.1154. Min Act: -0.1700
Data Index: 5118182 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.1467. Min Act: -0.1700
Data Index: 2944723 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.1467. Min Act: -0.1700
Data Index: 3048657 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6780. Min Range: -4.6780
Max Act: 4.1467. Min Act: -0.1700
Data Index: 6579999 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19