Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2279 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.8333. Min Act: -0.1700
Data Index: 527725 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.8333. Min Act: -0.1700
Data Index: 1676747 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.8333. Min Act: -0.1699
Data Index: 3960704 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7989. Min Act: -0.1700
Data Index: 7434135 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.8161. Min Act: -0.1700
Data Index: 7119716 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7989. Min Act: -0.1700
Data Index: 6958824 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7989. Min Act: -0.1700
Data Index: 1815217 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.8161. Min Act: -0.1700
Data Index: 5064007 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7989. Min Act: -0.1700
Data Index: 5701196 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7817. Min Act: -0.1700
Data Index: 2855747 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7817. Min Act: -0.1697
Data Index: 1030656 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7817. Min Act: -0.1700
Data Index: 6754392 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7817. Min Act: -0.1700
Data Index: 3673794 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7817. Min Act: -0.1700
Data Index: 869619 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7644. Min Act: -0.1700
Data Index: 7204947 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7558. Min Act: -0.1700
Data Index: 4729305 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7558. Min Act: -0.1700
Data Index: 6728993 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7644. Min Act: -0.1700
Data Index: 3618538 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7558. Min Act: -0.1700
Data Index: 316613 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8333. Min Range: -1.8333
Max Act: 1.7644. Min Act: -0.1700
Data Index: 1577405 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19