Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1076 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.5224. Min Act: -0.1700
Data Index: 1774807 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4982. Min Act: -0.1700
Data Index: 3264591 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4901. Min Act: -0.1700
Data Index: 2050263 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4941. Min Act: -0.1697
Data Index: 8510409 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4819. Min Act: -0.1700
Data Index: 6755066 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4901. Min Act: -0.1700
Data Index: 306379 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4819. Min Act: -0.1697
Data Index: 8055108 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4819. Min Act: -0.1700
Data Index: 2116577 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4779. Min Act: -0.1699
Data Index: 1858916 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4779. Min Act: -0.1700
Data Index: 4873568 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4738. Min Act: -0.1700
Data Index: 5966762 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4698. Min Act: -0.1689
Data Index: 1858915 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4657. Min Act: -0.1700
Data Index: 803367 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4698. Min Act: -0.1700
Data Index: 1700799 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4657. Min Act: -0.1690
Data Index: 1858917 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4617. Min Act: -0.1697
Data Index: 3058364 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4576. Min Act: -0.1700
Data Index: 5035355 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4617. Min Act: -0.1700
Data Index: 8167066 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4617. Min Act: -0.1700
Data Index: 7091005 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5224. Min Range: -2.5224
Max Act: 2.4495. Min Act: -0.1669
Data Index: 660676 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19