Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3762 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.9583. Min Act: -0.1700
Data Index: 650437 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.9108. Min Act: -0.1700
Data Index: 8664463 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.9108. Min Act: -0.1700
Data Index: 2883929 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.8949. Min Act: -0.1700
Data Index: 1927407 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.8949. Min Act: -0.1700
Data Index: 7128698 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.8949. Min Act: -0.1700
Data Index: 4022277 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.8473. Min Act: -0.1700
Data Index: 6758266 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.8155. Min Act: -0.1700
Data Index: 916235 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.8314. Min Act: -0.1700
Data Index: 5440707 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.7996. Min Act: -0.1700
Data Index: 1038403 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.7996. Min Act: -0.1700
Data Index: 1429060 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.7996. Min Act: -0.1700
Data Index: 5161673 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.7837. Min Act: -0.1700
Data Index: 5663350 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.7677. Min Act: -0.1700
Data Index: 6510468 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.7358. Min Act: -0.1700
Data Index: 4633251 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.7518. Min Act: -0.1700
Data Index: 1962812 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.7677. Min Act: -0.1700
Data Index: 7380432 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.7518. Min Act: -0.1700
Data Index: 6981068 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.7358. Min Act: -0.1700
Data Index: 6793864 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9583. Min Range: -2.9583
Max Act: 2.7518. Min Act: -0.1700
Data Index: 3714754 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19