Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4057 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.8130. Min Act: -0.1700
Data Index: 1727703 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.3443. Min Act: -0.1700
Data Index: 3171616 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.2505. Min Act: -0.1700
Data Index: 7616800 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.2193. Min Act: -0.1700
Data Index: 5778801 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.2193. Min Act: -0.1700
Data Index: 6809385 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.2193. Min Act: -0.1700
Data Index: 7175402 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.1880. Min Act: -0.1700
Data Index: 7412084 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.0943. Min Act: -0.1700
Data Index: 1289231 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.1255. Min Act: -0.1700
Data Index: 6218762 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.1568. Min Act: -0.1700
Data Index: 6003445 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.1568. Min Act: -0.1700
Data Index: 3485664 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.1568. Min Act: -0.1700
Data Index: 8790729 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.1255. Min Act: -0.1700
Data Index: 7490754 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.1255. Min Act: -0.1700
Data Index: 8308721 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.0943. Min Act: -0.1700
Data Index: 2971836 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.0630. Min Act: -0.1700
Data Index: 2813599 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.0318. Min Act: -0.1700
Data Index: 7768496 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.0630. Min Act: -0.1700
Data Index: 373617 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.0630. Min Act: -0.1700
Data Index: 6825769 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8130. Min Range: -6.8130
Max Act: 6.0005. Min Act: -0.1700
Data Index: 5619620 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19