Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 832 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0200. Min Range: -4.0200
Max Act: 4.0200. Min Act: -0.1700
Data Index: 6882857 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.8949. Min Act: -0.1700
Data Index: 2528791 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.8949. Min Act: -0.1700
Data Index: 1899734 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.8637. Min Act: -0.1700
Data Index: 2636659 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.8637. Min Act: -0.1700
Data Index: 2301415 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.8168. Min Act: -0.1700
Data Index: 3975000 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.8168. Min Act: -0.1700
Data Index: 4622159 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.7855. Min Act: -0.1700
Data Index: 7168334 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.7855. Min Act: -0.1700
Data Index: 7582534 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.8011. Min Act: -0.1700
Data Index: 1085103 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.8011. Min Act: -0.1700
Data Index: 8775085 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.7542. Min Act: -0.1700
Data Index: 7997755 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.7386. Min Act: -0.1700
Data Index: 253446 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.7229. Min Act: -0.1700
Data Index: 5607161 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.7386. Min Act: -0.1700
Data Index: 5640817 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.7229. Min Act: -0.1700
Data Index: 4315539 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.7073. Min Act: -0.1700
Data Index: 442902 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.7073. Min Act: -0.1700
Data Index: 6459544 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.6917. Min Act: -0.1700
Data Index: 5475401 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0200. Min Range: -4.0200
Max Act: 3.6760. Min Act: -0.1700
Data Index: 1112111 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19