Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 538 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.9695. Min Act: -0.1700
Data Index: 1082718 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.8757. Min Act: -0.1700
Data Index: 719889 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.8757. Min Act: -0.1700
Data Index: 450270 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.9070. Min Act: -0.1700
Data Index: 8082329 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.8445. Min Act: -0.1700
Data Index: 3502297 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.7820. Min Act: -0.1700
Data Index: 1280152 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.8132. Min Act: -0.1700
Data Index: 5079448 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.8132. Min Act: -0.1700
Data Index: 6444012 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.8132. Min Act: -0.1700
Data Index: 7553568 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.7820. Min Act: -0.1700
Data Index: 8365934 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.7820. Min Act: -0.1700
Data Index: 1507747 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.7507. Min Act: -0.1700
Data Index: 3291671 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.7507. Min Act: -0.1700
Data Index: 637997 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.7195. Min Act: -0.1700
Data Index: 2566042 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.7507. Min Act: -0.1700
Data Index: 4088603 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.7195. Min Act: -0.1700
Data Index: 2640690 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.7195. Min Act: -0.1700
Data Index: 1736446 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.7195. Min Act: -0.1700
Data Index: 5487130 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.6570. Min Act: -0.1700
Data Index: 523141 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9695. Min Range: -4.9695
Max Act: 4.6882. Min Act: -0.1700
Data Index: 4951387 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19