Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3271 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.3440. Min Act: -0.1700
Data Index: 1991169 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.3127. Min Act: -0.1700
Data Index: 211349 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.2498. Min Act: -0.1700
Data Index: 6924262 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.2184. Min Act: -0.1700
Data Index: 6750557 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1555. Min Act: -0.1700
Data Index: 3028215 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1555. Min Act: -0.1700
Data Index: 5848537 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1555. Min Act: -0.1700
Data Index: 6710395 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1555. Min Act: -0.1700
Data Index: 830786 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1555. Min Act: -0.1700
Data Index: 1206637 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1240. Min Act: -0.1700
Data Index: 4834773 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1555. Min Act: -0.1700
Data Index: 6587743 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1397. Min Act: -0.1700
Data Index: 5202920 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1397. Min Act: -0.1700
Data Index: 928875 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1240. Min Act: -0.1700
Data Index: 6582639 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1240. Min Act: -0.1700
Data Index: 2736542 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1240. Min Act: -0.1700
Data Index: 4139151 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1082. Min Act: -0.1700
Data Index: 7473989 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.0925. Min Act: -0.1700
Data Index: 5218466 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.1082. Min Act: -0.1700
Data Index: 1214889 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3440. Min Range: -3.3440
Max Act: 3.0925. Min Act: -0.1700
Data Index: 2135718 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19