Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3945. Min Range: -5.3945
Max Act: 5.3945. Min Act: -0.1700
Data Index: 5939414 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3945. Min Range: -5.3945
Max Act: 5.3008. Min Act: -0.1700
Data Index: 5893852 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3945. Min Range: -5.3945
Max Act: 5.2383. Min Act: -0.1700
Data Index: 4638104 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3945. Min Range: -5.3945
Max Act: 5.1758. Min Act: -0.1700
Data Index: 2770344 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3945. Min Range: -5.3945
Max Act: 5.1133. Min Act: -0.1700
Data Index: 4057933 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3945. Min Range: -5.3945
Max Act: 5.0820. Min Act: -0.1700
Data Index: 3765764 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3945. Min Range: -5.3945
Max Act: 5.0195. Min Act: -0.1700
Data Index: 71814 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3945. Min Range: -5.3945
Max Act: 5.0820. Min Act: -0.1700
Data Index: 5678465 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3945. Min Range: -5.3945
Max Act: 5.0195. Min Act: -0.1700
Data Index: 1404371 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3945. Min Range: -5.3945
Max Act: 4.9883. Min Act: -0.1700
Data Index: 1404372 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3945. Min Range: -5.3945
Max Act: 4.9570. Min Act: -0.1700
Data Index: 6151773 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3945. Min Range: -5.3945
Max Act: 4.9570. Min Act: -0.1700
Data Index: 4705448 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3945. Min Range: -5.3945
Max Act: 4.9570. Min Act: -0.1700
Data Index: 5882821 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3945. Min Range: -5.3945
Max Act: 4.9883. Min Act: -0.1700
Data Index: 1706004 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3945. Min Range: -5.3945
Max Act: 4.9258. Min Act: -0.1700
Data Index: 1711380 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3945. Min Range: -5.3945
Max Act: 4.9258. Min Act: -0.1700
Data Index: 3215859 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3945. Min Range: -5.3945
Max Act: 4.9258. Min Act: -0.1700
Data Index: 8395607 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3945. Min Range: -5.3945
Max Act: 4.9570. Min Act: -0.1700
Data Index: 7401907 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3945. Min Range: -5.3945
Max Act: 4.9570. Min Act: -0.1700
Data Index: 6940149 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3945. Min Range: -5.3945
Max Act: 4.9570. Min Act: -0.1700
Data Index: 6380152 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19