Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1413 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.4470. Min Act: -0.1700
Data Index: 5603027 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.4470. Min Act: -0.1700
Data Index: 4647213 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.3845. Min Act: -0.1700
Data Index: 3660992 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.3845. Min Act: -0.1700
Data Index: 3010977 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.3220. Min Act: -0.1700
Data Index: 6210861 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.3220. Min Act: -0.1700
Data Index: 2323657 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.3220. Min Act: -0.1700
Data Index: 6974539 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.3220. Min Act: -0.1700
Data Index: 4942901 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.2595. Min Act: -0.1700
Data Index: 1606972 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.1970. Min Act: -0.1700
Data Index: 8023778 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.1970. Min Act: -0.1700
Data Index: 3886084 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.1970. Min Act: -0.1700
Data Index: 2210558 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.1970. Min Act: -0.1700
Data Index: 7179285 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.1345. Min Act: -0.1700
Data Index: 5915810 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.1345. Min Act: -0.1700
Data Index: 491961 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.1345. Min Act: -0.1700
Data Index: 2838064 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.1345. Min Act: -0.1700
Data Index: 2342785 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.1345. Min Act: -0.1700
Data Index: 586865 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.1033. Min Act: -0.1700
Data Index: 5195768 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4470. Min Range: -8.4470
Max Act: 8.1345. Min Act: -0.1700
Data Index: 4300712 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19