Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0664. Min Range: -8.0664
Max Act: 8.0664. Min Act: -0.1700
Data Index: 4204365 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.9102. Min Act: -0.1700
Data Index: 4165150 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.8789. Min Act: -0.1700
Data Index: 2054060 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.6602. Min Act: -0.1700
Data Index: 6423889 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.3477. Min Act: -0.1700
Data Index: 1409608 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.3164. Min Act: -0.1700
Data Index: 7620826 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.2852. Min Act: -0.1700
Data Index: 4119526 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.2852. Min Act: -0.1700
Data Index: 661613 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.2852. Min Act: -0.1700
Data Index: 2536715 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.2227. Min Act: -0.1700
Data Index: 1427814 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.2227. Min Act: -0.1700
Data Index: 4705140 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.2227. Min Act: -0.1700
Data Index: 6794599 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.2227. Min Act: -0.1700
Data Index: 1666732 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.2227. Min Act: -0.1700
Data Index: 2479463 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.1602. Min Act: -0.1700
Data Index: 5746681 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.1602. Min Act: -0.1700
Data Index: 6629404 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.1602. Min Act: -0.1700
Data Index: 5814615 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.1914. Min Act: -0.1700
Data Index: 421281 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.1914. Min Act: -0.1700
Data Index: 497693 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0664. Min Range: -8.0664
Max Act: 7.1914. Min Act: -0.1700
Data Index: 6635714 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19