Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1694 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2815. Min Range: -8.2815
Max Act: 8.2815. Min Act: -0.1700
Data Index: 1407222 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2815. Min Range: -8.2815
Max Act: 8.1565. Min Act: -0.1700
Data Index: 1552761 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.9065. Min Act: -0.1700
Data Index: 3439888 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.9690. Min Act: -0.1700
Data Index: 1753526 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.9065. Min Act: -0.1700
Data Index: 1488341 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.9690. Min Act: -0.1700
Data Index: 2146044 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.8440. Min Act: -0.1700
Data Index: 5293026 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.7815. Min Act: -0.1700
Data Index: 4318607 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.7815. Min Act: -0.1700
Data Index: 2903837 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.7815. Min Act: -0.1700
Data Index: 8383730 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.7815. Min Act: -0.1700
Data Index: 8503225 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.7815. Min Act: -0.1700
Data Index: 7340186 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.7815. Min Act: -0.1700
Data Index: 2450422 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.7190. Min Act: -0.1700
Data Index: 2517455 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.6877. Min Act: -0.1700
Data Index: 5265360 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.7190. Min Act: -0.1700
Data Index: 3819368 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.7190. Min Act: -0.1700
Data Index: 5039293 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.7190. Min Act: -0.1700
Data Index: 740936 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.7190. Min Act: -0.1700
Data Index: 5747044 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2815. Min Range: -8.2815
Max Act: 7.7190. Min Act: -0.1700
Data Index: 7704176 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19