Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5656 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2430. Min Range: -9.2430
Max Act: 9.2430. Min Act: -0.1700
Data Index: 5278183 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2430. Min Range: -9.2430
Max Act: 9.1805. Min Act: -0.1700
Data Index: 4280971 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2430. Min Range: -9.2430
Max Act: 9.1805. Min Act: -0.1700
Data Index: 5204017 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2430. Min Range: -9.2430
Max Act: 9.1180. Min Act: -0.1700
Data Index: 5035757 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.8055. Min Act: -0.1700
Data Index: 8667300 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.6805. Min Act: -0.1700
Data Index: 6750819 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.6805. Min Act: -0.1700
Data Index: 4397129 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.6180. Min Act: -0.1700
Data Index: 4363856 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.6180. Min Act: -0.1700
Data Index: 5926691 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.5555. Min Act: -0.1700
Data Index: 21527 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.5555. Min Act: -0.1700
Data Index: 3447537 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.4930. Min Act: -0.1700
Data Index: 7139948 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.4930. Min Act: -0.1700
Data Index: 2445827 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.4305. Min Act: -0.1700
Data Index: 3304382 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.5555. Min Act: -0.1700
Data Index: 6779886 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.4930. Min Act: -0.1700
Data Index: 1960764 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.4305. Min Act: -0.1700
Data Index: 2500533 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.4305. Min Act: -0.1700
Data Index: 8320369 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.4305. Min Act: -0.1700
Data Index: 145612 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2430. Min Range: -9.2430
Max Act: 8.4930. Min Act: -0.1700
Data Index: 1605647 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19