Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3285 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8364. Min Range: -8.8364
Max Act: 8.8364. Min Act: -0.1700
Data Index: 6607210 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8364. Min Range: -8.8364
Max Act: 8.2739. Min Act: -0.1700
Data Index: 681520 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8364. Min Range: -8.8364
Max Act: 8.0239. Min Act: -0.1700
Data Index: 5584753 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.9926. Min Act: -0.1700
Data Index: 3754617 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.9301. Min Act: -0.1700
Data Index: 2015038 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.8364. Min Act: -0.1700
Data Index: 4940463 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.8051. Min Act: -0.1700
Data Index: 7301700 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.8051. Min Act: -0.1700
Data Index: 687295 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.7426. Min Act: -0.1700
Data Index: 2148119 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.6801. Min Act: -0.1700
Data Index: 7438761 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.7114. Min Act: -0.1700
Data Index: 600866 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.6489. Min Act: -0.1700
Data Index: 5757120 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.6176. Min Act: -0.1700
Data Index: 5955682 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.6176. Min Act: -0.1700
Data Index: 2276484 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.6176. Min Act: -0.1700
Data Index: 7789563 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.5864. Min Act: -0.1700
Data Index: 739879 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.6176. Min Act: -0.1700
Data Index: 5344288 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.5864. Min Act: -0.1700
Data Index: 4267086 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.5864. Min Act: -0.1700
Data Index: 5802823 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8364. Min Range: -8.8364
Max Act: 7.5864. Min Act: -0.1700
Data Index: 7538592 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19