Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1233 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.7616. Min Act: -0.1700
Data Index: 3262412 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.6991. Min Act: -0.1700
Data Index: 322762 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.6366. Min Act: -0.1700
Data Index: 8454076 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.5429. Min Act: -0.1700
Data Index: 2070703 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.5429. Min Act: -0.1700
Data Index: 6768931 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.5116. Min Act: -0.1700
Data Index: 1478928 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4804. Min Act: -0.1700
Data Index: 6635750 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4804. Min Act: -0.1700
Data Index: 2070700 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4804. Min Act: -0.1700
Data Index: 926293 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4804. Min Act: -0.1700
Data Index: 5435257 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4491. Min Act: -0.1700
Data Index: 377930 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4491. Min Act: -0.1700
Data Index: 1468194 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4491. Min Act: -0.1700
Data Index: 4461114 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4491. Min Act: -0.1700
Data Index: 8617937 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4179. Min Act: -0.1700
Data Index: 2070705 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4179. Min Act: -0.1700
Data Index: 3848873 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4179. Min Act: -0.1700
Data Index: 1141121 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4179. Min Act: -0.1700
Data Index: 6793301 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.3866. Min Act: -0.1700
Data Index: 6866748 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4179. Min Act: -0.1700
Data Index: 3012301 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19