Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 890 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.5153. Min Act: -0.1700
Data Index: 7989595 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.4528. Min Act: -0.1700
Data Index: 587575 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.4528. Min Act: -0.1700
Data Index: 5641766 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.4528. Min Act: -0.1700
Data Index: 6670058 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.4215. Min Act: -0.1700
Data Index: 1973638 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.3903. Min Act: -0.1700
Data Index: 1287924 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.3590. Min Act: -0.1700
Data Index: 8141857 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.3590. Min Act: -0.1700
Data Index: 2148008 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.3903. Min Act: -0.1700
Data Index: 3117798 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.3590. Min Act: -0.1700
Data Index: 2337666 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.3278. Min Act: -0.1700
Data Index: 4891748 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.3278. Min Act: -0.1700
Data Index: 8275060 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.3278. Min Act: -0.1700
Data Index: 7442266 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.3278. Min Act: -0.1700
Data Index: 2196503 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.2653. Min Act: -0.1700
Data Index: 4147569 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.2965. Min Act: -0.1700
Data Index: 3270561 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.2965. Min Act: -0.1700
Data Index: 2017241 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.2965. Min Act: -0.1700
Data Index: 3781523 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.2965. Min Act: -0.1700
Data Index: 1452872 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5153. Min Range: -5.5153
Max Act: 5.2340. Min Act: -0.1700
Data Index: 865564 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19