Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.2056. Min Act: -0.1700
Data Index: 2646110 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.1742. Min Act: -0.1700
Data Index: 7586311 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.1427. Min Act: -0.1700
Data Index: 8242008 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.1427. Min Act: -0.1700
Data Index: 3404101 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.1427. Min Act: -0.1700
Data Index: 7373496 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.1112. Min Act: -0.1700
Data Index: 8373334 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.1270. Min Act: -0.1700
Data Index: 7743509 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.1112. Min Act: -0.1700
Data Index: 2229951 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.0797. Min Act: -0.1700
Data Index: 4438291 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.0481. Min Act: -0.1700
Data Index: 6169417 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.0481. Min Act: -0.1700
Data Index: 35342 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.0481. Min Act: -0.1700
Data Index: 8154958 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.0323. Min Act: -0.1700
Data Index: 5388469 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.0166. Min Act: -0.1700
Data Index: 2644511 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.0166. Min Act: -0.1700
Data Index: 6904771 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.0166. Min Act: -0.1700
Data Index: 8217460 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.0008. Min Act: -0.1700
Data Index: 2995625 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.0008. Min Act: -0.1700
Data Index: 7462397 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.0008. Min Act: -0.1700
Data Index: 4086873 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2056. Min Range: -3.2056
Max Act: 3.0008. Min Act: -0.1700
Data Index: 7131196 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19