Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4256 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.5039. Min Act: -0.1700
Data Index: 5335484 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.5039. Min Act: -0.1700
Data Index: 3961283 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.4725. Min Act: -0.1700
Data Index: 2243551 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.4255. Min Act: -0.1700
Data Index: 5126909 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.4255. Min Act: -0.1700
Data Index: 2704002 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.4099. Min Act: -0.1700
Data Index: 8577163 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.3628. Min Act: -0.1700
Data Index: 4028883 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.3314. Min Act: -0.1700
Data Index: 6452197 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.3471. Min Act: -0.1700
Data Index: 8381363 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.3471. Min Act: -0.1700
Data Index: 3082522 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.3157. Min Act: -0.1700
Data Index: 2098081 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.3157. Min Act: -0.1700
Data Index: 5382398 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.3157. Min Act: -0.1700
Data Index: 6762643 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.2372. Min Act: -0.1700
Data Index: 8364375 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.2215. Min Act: -0.1700
Data Index: 5234693 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.2372. Min Act: -0.1700
Data Index: 615080 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.2372. Min Act: -0.1700
Data Index: 5109126 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.2215. Min Act: -0.1700
Data Index: 3733357 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.2529. Min Act: -0.1700
Data Index: 2958566 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5039. Min Range: -3.5039
Max Act: 3.2372. Min Act: -0.1700
Data Index: 8380924 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19