Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5180 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2207. Min Range: -6.2207
Max Act: 6.1895. Min Act: -0.1700
Data Index: 3653604 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2207. Min Range: -6.2207
Max Act: 6.2207. Min Act: -0.1700
Data Index: 552111 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2207. Min Range: -6.2207
Max Act: 6.0957. Min Act: -0.1700
Data Index: 154582 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.9395. Min Act: -0.1700
Data Index: 7803253 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.8770. Min Act: -0.1700
Data Index: 1246863 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.8457. Min Act: -0.1700
Data Index: 5569848 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.8457. Min Act: -0.1700
Data Index: 373096 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.8145. Min Act: -0.1700
Data Index: 3989532 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.7520. Min Act: -0.1700
Data Index: 5167836 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.7832. Min Act: -0.1700
Data Index: 3001524 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.7520. Min Act: -0.1700
Data Index: 4856006 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.7520. Min Act: -0.1700
Data Index: 6899371 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.7207. Min Act: -0.1700
Data Index: 673152 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.7207. Min Act: -0.1700
Data Index: 6123183 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.7207. Min Act: -0.1700
Data Index: 7688554 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.6895. Min Act: -0.1700
Data Index: 5661463 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.7207. Min Act: -0.1700
Data Index: 5518625 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.6895. Min Act: -0.1700
Data Index: 7067575 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.7207. Min Act: -0.1700
Data Index: 5604474 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2207. Min Range: -6.2207
Max Act: 5.6895. Min Act: -0.1700
Data Index: 1051082 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19