Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3662 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0365. Min Range: -6.0365
Max Act: 6.0365. Min Act: -0.1700
Data Index: 4001570 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0365. Min Range: -6.0365
Max Act: 6.0053. Min Act: -0.1700
Data Index: 1458524 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.9740. Min Act: -0.1700
Data Index: 2549385 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.9428. Min Act: -0.1700
Data Index: 7172649 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.9115. Min Act: -0.1700
Data Index: 395490 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.9115. Min Act: -0.1700
Data Index: 1607062 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.8803. Min Act: -0.1700
Data Index: 3585536 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.8490. Min Act: -0.1700
Data Index: 8199186 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.8490. Min Act: -0.1700
Data Index: 8454304 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.8178. Min Act: -0.1700
Data Index: 1430271 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.8178. Min Act: -0.1700
Data Index: 8009740 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.8178. Min Act: -0.1700
Data Index: 3212744 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.8490. Min Act: -0.1700
Data Index: 6968344 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.7553. Min Act: -0.1700
Data Index: 1698175 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.8178. Min Act: -0.1700
Data Index: 6899148 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.7553. Min Act: -0.1700
Data Index: 7630270 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.7553. Min Act: -0.1700
Data Index: 1208133 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.7553. Min Act: -0.1700
Data Index: 3239294 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.7553. Min Act: -0.1700
Data Index: 3500448 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0365. Min Range: -6.0365
Max Act: 5.7865. Min Act: -0.1700
Data Index: 5002880 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19