Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3899 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2463. Min Range: -4.2463
Max Act: 4.2463. Min Act: -0.1700
Data Index: 782652 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.9650. Min Act: -0.1700
Data Index: 4418585 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.8087. Min Act: -0.1700
Data Index: 3605881 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.8712. Min Act: -0.1700
Data Index: 7216538 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.8087. Min Act: -0.1700
Data Index: 7229771 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.8712. Min Act: -0.1700
Data Index: 2460070 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.8087. Min Act: -0.1700
Data Index: 7587335 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.7774. Min Act: -0.1700
Data Index: 1717332 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.8399. Min Act: -0.1700
Data Index: 3946824 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.7774. Min Act: -0.1700
Data Index: 7339759 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.8087. Min Act: -0.1700
Data Index: 586625 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.7774. Min Act: -0.1700
Data Index: 3286445 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.7461. Min Act: -0.1700
Data Index: 4865357 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.7148. Min Act: -0.1700
Data Index: 7574914 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.7148. Min Act: -0.1700
Data Index: 7189033 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.7148. Min Act: -0.1700
Data Index: 992284 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.6835. Min Act: -0.1700
Data Index: 7191739 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.6835. Min Act: -0.1700
Data Index: 5053119 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.6835. Min Act: -0.1700
Data Index: 6988838 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2463. Min Range: -4.2463
Max Act: 3.6835. Min Act: -0.1700
Data Index: 2966938 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19