Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1123 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8698. Min Range: -8.8698
Max Act: 8.8698. Min Act: -0.1700
Data Index: 3136172 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8698. Min Range: -8.8698
Max Act: 8.6198. Min Act: -0.1700
Data Index: 506466 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8698. Min Range: -8.8698
Max Act: 8.4948. Min Act: -0.1700
Data Index: 2529901 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8698. Min Range: -8.8698
Max Act: 8.4948. Min Act: -0.1700
Data Index: 359180 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8698. Min Range: -8.8698
Max Act: 8.4323. Min Act: -0.1700
Data Index: 5083723 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8698. Min Range: -8.8698
Max Act: 8.4323. Min Act: -0.1700
Data Index: 7631147 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8698. Min Range: -8.8698
Max Act: 8.1510. Min Act: -0.1700
Data Index: 8206790 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8698. Min Range: -8.8698
Max Act: 8.1510. Min Act: -0.1700
Data Index: 4629695 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8698. Min Range: -8.8698
Max Act: 8.1510. Min Act: -0.1700
Data Index: 585696 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8698. Min Range: -8.8698
Max Act: 8.1198. Min Act: -0.1700
Data Index: 7464493 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8698. Min Range: -8.8698
Max Act: 8.0885. Min Act: -0.1700
Data Index: 1337541 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8698. Min Range: -8.8698
Max Act: 7.9948. Min Act: -0.1700
Data Index: 2695210 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8698. Min Range: -8.8698
Max Act: 7.9635. Min Act: -0.1700
Data Index: 2079051 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8698. Min Range: -8.8698
Max Act: 7.9948. Min Act: -0.1700
Data Index: 7378632 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8698. Min Range: -8.8698
Max Act: 7.9635. Min Act: -0.1700
Data Index: 6967050 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8698. Min Range: -8.8698
Max Act: 7.9010. Min Act: -0.1700
Data Index: 2631151 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8698. Min Range: -8.8698
Max Act: 7.8385. Min Act: -0.1700
Data Index: 270040 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8698. Min Range: -8.8698
Max Act: 7.9010. Min Act: -0.1700
Data Index: 3336379 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8698. Min Range: -8.8698
Max Act: 7.8385. Min Act: -0.1700
Data Index: 2075187 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8698. Min Range: -8.8698
Max Act: 7.8385. Min Act: -0.1700
Data Index: 351048 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19