Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.6537. Min Act: -0.1700
Data Index: 666150 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.5733. Min Act: -0.1700
Data Index: 3446726 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.5087. Min Act: -0.1700
Data Index: 7830659 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.5087. Min Act: -0.1700
Data Index: 6323397 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.5087. Min Act: -0.1700
Data Index: 3498142 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.5087. Min Act: -0.1700
Data Index: 4574435 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.5087. Min Act: -0.1700
Data Index: 7495365 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.4763. Min Act: -0.1700
Data Index: 4734653 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.4763. Min Act: -0.1700
Data Index: 4763214 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.4763. Min Act: -0.1700
Data Index: 7297973 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.4763. Min Act: -0.1700
Data Index: 7650372 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.4600. Min Act: -0.1700
Data Index: 2269063 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.4600. Min Act: -0.1700
Data Index: 689402 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.4600. Min Act: -0.1700
Data Index: 3161036 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.4438. Min Act: -0.1700
Data Index: 5000939 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.4600. Min Act: -0.1700
Data Index: 6871790 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.4438. Min Act: -0.1700
Data Index: 2824739 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.4438. Min Act: -0.1700
Data Index: 3567262 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.4438. Min Act: -0.1700
Data Index: 3857136 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6537. Min Range: -2.6537
Max Act: 2.4600. Min Act: -0.1700
Data Index: 3905896 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19