Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2778 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3751. Min Range: -7.3751
Max Act: 7.3751. Min Act: -0.1700
Data Index: 8250957 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3751. Min Range: -7.3751
Max Act: 7.3751. Min Act: -0.1700
Data Index: 7829403 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3751. Min Range: -7.3751
Max Act: 7.3126. Min Act: -0.1700
Data Index: 2048234 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3751. Min Range: -7.3751
Max Act: 7.2188. Min Act: -0.1700
Data Index: 808226 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3751. Min Range: -7.3751
Max Act: 7.1876. Min Act: -0.1700
Data Index: 5269628 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3751. Min Range: -7.3751
Max Act: 7.0001. Min Act: -0.1700
Data Index: 7101768 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.9376. Min Act: -0.1700
Data Index: 8535840 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.9376. Min Act: -0.1700
Data Index: 6139849 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.8751. Min Act: -0.1700
Data Index: 2307176 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.8438. Min Act: -0.1700
Data Index: 8285274 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.8126. Min Act: -0.1700
Data Index: 4131712 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.7813. Min Act: -0.1700
Data Index: 265975 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.7813. Min Act: -0.1700
Data Index: 2633351 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.7501. Min Act: -0.1700
Data Index: 1033146 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.7501. Min Act: -0.1700
Data Index: 4639432 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.7501. Min Act: -0.1700
Data Index: 2932856 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.7188. Min Act: -0.1700
Data Index: 7985771 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.7188. Min Act: -0.1700
Data Index: 6481416 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.7501. Min Act: -0.1700
Data Index: 2284153 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3751. Min Range: -7.3751
Max Act: 6.7188. Min Act: -0.1700
Data Index: 1148610 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19