Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5057 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7483. Min Range: -4.7483
Max Act: 4.7483. Min Act: -0.1700
Data Index: 1963068 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7483. Min Range: -4.7483
Max Act: 4.1545. Min Act: -0.1700
Data Index: 3572917 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7483. Min Range: -4.7483
Max Act: 4.1545. Min Act: -0.1700
Data Index: 29875 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7483. Min Range: -4.7483
Max Act: 4.1232. Min Act: -0.1700
Data Index: 4167974 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7483. Min Range: -4.7483
Max Act: 4.0920. Min Act: -0.1700
Data Index: 7819445 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7483. Min Range: -4.7483
Max Act: 4.0920. Min Act: -0.1700
Data Index: 3474663 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7483. Min Range: -4.7483
Max Act: 4.0607. Min Act: -0.1700
Data Index: 3323607 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7483. Min Range: -4.7483
Max Act: 4.0607. Min Act: -0.1700
Data Index: 7195595 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7483. Min Range: -4.7483
Max Act: 4.0294. Min Act: -0.1700
Data Index: 7644293 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7483. Min Range: -4.7483
Max Act: 4.0294. Min Act: -0.1700
Data Index: 5410268 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7483. Min Range: -4.7483
Max Act: 3.9982. Min Act: -0.1700
Data Index: 1506909 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7483. Min Range: -4.7483
Max Act: 4.0294. Min Act: -0.1700
Data Index: 8107584 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7483. Min Range: -4.7483
Max Act: 3.9982. Min Act: -0.1700
Data Index: 3963112 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7483. Min Range: -4.7483
Max Act: 3.9669. Min Act: -0.1700
Data Index: 6901305 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7483. Min Range: -4.7483
Max Act: 3.9982. Min Act: -0.1700
Data Index: 2956085 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7483. Min Range: -4.7483
Max Act: 3.9982. Min Act: -0.1700
Data Index: 5759895 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7483. Min Range: -4.7483
Max Act: 3.9669. Min Act: -0.1700
Data Index: 4070398 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7483. Min Range: -4.7483
Max Act: 3.9982. Min Act: -0.1700
Data Index: 6814816 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7483. Min Range: -4.7483
Max Act: 3.9669. Min Act: -0.1700
Data Index: 1800280 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7483. Min Range: -4.7483
Max Act: 3.9669. Min Act: -0.1700
Data Index: 7595532 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19