Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3184 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.9886. Min Act: -0.1700
Data Index: 5768448 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.8323. Min Act: -0.1700
Data Index: 4197386 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.8323. Min Act: -0.1700
Data Index: 2614172 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.8323. Min Act: -0.1700
Data Index: 8662648 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.8323. Min Act: -0.1700
Data Index: 7053449 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.8011. Min Act: -0.1700
Data Index: 1845652 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.7698. Min Act: -0.1700
Data Index: 8245129 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.8011. Min Act: -0.1700
Data Index: 1522538 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.8323. Min Act: -0.1700
Data Index: 4192174 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.8323. Min Act: -0.1700
Data Index: 5478870 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.7698. Min Act: -0.1700
Data Index: 2190129 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.8011. Min Act: -0.1700
Data Index: 4782904 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.7386. Min Act: -0.1700
Data Index: 4516384 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.7073. Min Act: -0.1700
Data Index: 1265371 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.6761. Min Act: -0.1700
Data Index: 6729935 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.6761. Min Act: -0.1700
Data Index: 4479224 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.6761. Min Act: -0.1700
Data Index: 2463994 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.6761. Min Act: -0.1700
Data Index: 4350589 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.6448. Min Act: -0.1700
Data Index: 4401691 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9886. Min Range: -6.9886
Max Act: 6.6448. Min Act: -0.1700
Data Index: 4548116 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19