Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3821 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0899. Min Range: -4.0899
Max Act: 4.0899. Min Act: -0.1700
Data Index: 5173216 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.9649. Min Act: -0.1700
Data Index: 1903246 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.9336. Min Act: -0.1700
Data Index: 3480059 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.9336. Min Act: -0.1700
Data Index: 6476442 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.9023. Min Act: -0.1700
Data Index: 5884210 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.8711. Min Act: -0.1700
Data Index: 5173220 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.8711. Min Act: -0.1700
Data Index: 2472908 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.8711. Min Act: -0.1700
Data Index: 3260466 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.8398. Min Act: -0.1700
Data Index: 5497062 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.8398. Min Act: -0.1700
Data Index: 5412830 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.8398. Min Act: -0.1700
Data Index: 1861964 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.8398. Min Act: -0.1700
Data Index: 6507718 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.8085. Min Act: -0.1700
Data Index: 2512840 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.8085. Min Act: -0.1700
Data Index: 6560659 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.8085. Min Act: -0.1700
Data Index: 2551163 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.8085. Min Act: -0.1700
Data Index: 8447814 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.7772. Min Act: -0.1700
Data Index: 1673537 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.7772. Min Act: -0.1700
Data Index: 7376867 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.7772. Min Act: -0.1700
Data Index: 3596110 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0899. Min Range: -4.0899
Max Act: 3.7772. Min Act: -0.1700
Data Index: 5435466 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19