Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 478 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.7840. Min Act: -0.1700
Data Index: 8790685 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.7840. Min Act: -0.1700
Data Index: 7358530 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.7215. Min Act: -0.1700
Data Index: 6203027 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.6590. Min Act: -0.1700
Data Index: 2107157 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.6278. Min Act: -0.1700
Data Index: 2466228 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.6278. Min Act: -0.1700
Data Index: 4671073 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.5965. Min Act: -0.1700
Data Index: 8012638 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.5965. Min Act: -0.1700
Data Index: 2466048 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.5965. Min Act: -0.1700
Data Index: 8787931 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.5028. Min Act: -0.1700
Data Index: 7517282 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.5028. Min Act: -0.1700
Data Index: 718099 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.4715. Min Act: -0.1700
Data Index: 5336877 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.4715. Min Act: -0.1700
Data Index: 3179897 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.4090. Min Act: -0.1700
Data Index: 8709894 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.4403. Min Act: -0.1700
Data Index: 6762429 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.4403. Min Act: -0.1700
Data Index: 7215794 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.4090. Min Act: -0.1700
Data Index: 3661696 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.3778. Min Act: -0.1700
Data Index: 3627443 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.3465. Min Act: -0.1700
Data Index: 8389917 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.3465. Min Act: -0.1700
Data Index: 8533231 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19