Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3397 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.2919. Min Act: -0.1700
Data Index: 4240392 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.0731. Min Act: -0.1700
Data Index: 6651310 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.0731. Min Act: -0.1700
Data Index: 2016728 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.0106. Min Act: -0.1700
Data Index: 8210967 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.9481. Min Act: -0.1700
Data Index: 6349809 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.8231. Min Act: -0.1700
Data Index: 389667 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7919. Min Act: -0.1700
Data Index: 4177687 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7919. Min Act: -0.1700
Data Index: 6244791 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7919. Min Act: -0.1700
Data Index: 3822911 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7606. Min Act: -0.1700
Data Index: 2274862 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7606. Min Act: -0.1700
Data Index: 7571456 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7606. Min Act: -0.1700
Data Index: 247760 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7294. Min Act: -0.1700
Data Index: 209315 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7919. Min Act: -0.1700
Data Index: 639224 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7294. Min Act: -0.1700
Data Index: 4316215 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.6981. Min Act: -0.1700
Data Index: 8248838 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7294. Min Act: -0.1700
Data Index: 8329732 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7294. Min Act: -0.1700
Data Index: 4874148 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.6981. Min Act: -0.1700
Data Index: 7673108 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.6981. Min Act: -0.1700
Data Index: 7148401 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19