Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5096 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.9499. Min Act: -0.1700
Data Index: 5284929 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.8874. Min Act: -0.1700
Data Index: 5178689 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.8874. Min Act: -0.1700
Data Index: 2592064 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.8874. Min Act: -0.1700
Data Index: 4600372 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.8249. Min Act: -0.1700
Data Index: 1617533 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.6999. Min Act: -0.1700
Data Index: 7729518 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.6999. Min Act: -0.1700
Data Index: 8779226 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.6687. Min Act: -0.1700
Data Index: 6077305 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.6374. Min Act: -0.1700
Data Index: 3036292 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.6062. Min Act: -0.1700
Data Index: 7321045 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.6374. Min Act: -0.1700
Data Index: 6016784 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.6374. Min Act: -0.1700
Data Index: 80092 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.6062. Min Act: -0.1700
Data Index: 7453078 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.6062. Min Act: -0.1700
Data Index: 4174082 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.5749. Min Act: -0.1700
Data Index: 4893840 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.5749. Min Act: -0.1700
Data Index: 7073332 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.5749. Min Act: -0.1700
Data Index: 5225115 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.5749. Min Act: -0.1700
Data Index: 1241935 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.5749. Min Act: -0.1700
Data Index: 1175488 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9499. Min Range: -7.9499
Max Act: 7.5437. Min Act: -0.1700
Data Index: 7351035 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19