Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3222 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0675. Min Range: -6.0675
Max Act: 6.0675. Min Act: -0.1696
Data Index: 7715171 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.9112. Min Act: -0.1700
Data Index: 3499218 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.9112. Min Act: -0.1657
Data Index: 224034 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.8487. Min Act: -0.1693
Data Index: 195197 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.8487. Min Act: -0.1700
Data Index: 4327993 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.8175. Min Act: -0.1700
Data Index: 1732862 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.7862. Min Act: -0.1700
Data Index: 8461197 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.7550. Min Act: -0.1700
Data Index: 3267055 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.7550. Min Act: -0.1700
Data Index: 3291300 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.7550. Min Act: -0.1700
Data Index: 8488351 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.7237. Min Act: -0.1700
Data Index: 6492938 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.7237. Min Act: -0.1700
Data Index: 1147181 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.6925. Min Act: -0.1700
Data Index: 8461195 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.6612. Min Act: -0.1673
Data Index: 3138016 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.6612. Min Act: -0.1700
Data Index: 8461196 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.6612. Min Act: -0.1700
Data Index: 5799492 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.6612. Min Act: -0.1699
Data Index: 8256571 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.6612. Min Act: -0.1700
Data Index: 2996680 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.6300. Min Act: -0.1456
Data Index: 997147 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0675. Min Range: -6.0675
Max Act: 5.6300. Min Act: -0.1700
Data Index: 2517465 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19