Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2204 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3794. Min Range: -9.3794
Max Act: 9.3794. Min Act: -0.1700
Data Index: 535672 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3794. Min Range: -9.3794
Max Act: 9.1294. Min Act: -0.1700
Data Index: 3822559 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3794. Min Range: -9.3794
Max Act: 9.0669. Min Act: -0.1700
Data Index: 6045626 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.9419. Min Act: -0.1700
Data Index: 5977173 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.8794. Min Act: -0.1700
Data Index: 6014467 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.8794. Min Act: -0.1700
Data Index: 1392159 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.8169. Min Act: -0.1700
Data Index: 907285 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.8169. Min Act: -0.1700
Data Index: 2275898 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.8169. Min Act: -0.1700
Data Index: 2232502 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.6919. Min Act: -0.1700
Data Index: 4983076 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.6919. Min Act: -0.1700
Data Index: 460059 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.6919. Min Act: -0.1700
Data Index: 6834180 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.6294. Min Act: -0.1700
Data Index: 8416531 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.6294. Min Act: -0.1700
Data Index: 8315852 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.5669. Min Act: -0.1700
Data Index: 8237286 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.6294. Min Act: -0.1700
Data Index: 995713 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.6294. Min Act: -0.1700
Data Index: 3187525 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.6294. Min Act: -0.1700
Data Index: 1549686 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.6294. Min Act: -0.1700
Data Index: 1340585 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3794. Min Range: -9.3794
Max Act: 8.5669. Min Act: -0.1700
Data Index: 633880 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19