Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1113 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.7087. Min Act: -0.1700
Data Index: 1067632 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.7087. Min Act: -0.1700
Data Index: 1792411 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.7087. Min Act: -0.1700
Data Index: 8015801 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.7087. Min Act: -0.1700
Data Index: 7543809 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.6774. Min Act: -0.1700
Data Index: 2809730 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.6774. Min Act: -0.1700
Data Index: 2115054 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.6149. Min Act: -0.1700
Data Index: 3957125 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.6149. Min Act: -0.1700
Data Index: 6277277 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.5524. Min Act: -0.1700
Data Index: 8108993 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.5212. Min Act: -0.1700
Data Index: 4695605 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.5212. Min Act: -0.1700
Data Index: 7633387 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.4899. Min Act: -0.1700
Data Index: 8615719 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.4899. Min Act: -0.1700
Data Index: 537188 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.4899. Min Act: -0.1700
Data Index: 6925019 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.4587. Min Act: -0.1700
Data Index: 3198363 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.4274. Min Act: -0.1700
Data Index: 8595210 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.4274. Min Act: -0.1700
Data Index: 1901534 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.4274. Min Act: -0.1700
Data Index: 6507672 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.4274. Min Act: -0.1700
Data Index: 5479537 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.4274. Min Act: -0.1700
Data Index: 8217776 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19