Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.7892. Min Act: -0.1700
Data Index: 556694 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.6642. Min Act: -0.1700
Data Index: 2691110 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.6330. Min Act: -0.1700
Data Index: 8615441 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.6017. Min Act: -0.1700
Data Index: 3693118 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.6017. Min Act: -0.1700
Data Index: 236959 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.5705. Min Act: -0.1700
Data Index: 4387677 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.5392. Min Act: -0.1700
Data Index: 5372188 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.5080. Min Act: -0.1700
Data Index: 8472202 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.5080. Min Act: -0.1700
Data Index: 7713749 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.4455. Min Act: -0.1700
Data Index: 2479430 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.3830. Min Act: -0.1700
Data Index: 247975 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.3830. Min Act: -0.1700
Data Index: 6907 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.3830. Min Act: -0.1700
Data Index: 273670 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.3830. Min Act: -0.1700
Data Index: 2564158 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.3830. Min Act: -0.1700
Data Index: 861515 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.3517. Min Act: -0.1700
Data Index: 8645993 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.3205. Min Act: -0.1700
Data Index: 7792255 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.3517. Min Act: -0.1700
Data Index: 7772719 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.3517. Min Act: -0.1700
Data Index: 7497034 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7892. Min Range: -6.7892
Max Act: 6.3517. Min Act: -0.1700
Data Index: 7013713 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19