Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4075 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8082. Min Range: -6.8082
Max Act: 6.8082. Min Act: -0.1700
Data Index: 7790679 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8082. Min Range: -6.8082
Max Act: 6.3394. Min Act: -0.1700
Data Index: 1221853 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8082. Min Range: -6.8082
Max Act: 6.3394. Min Act: -0.1700
Data Index: 7296794 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8082. Min Range: -6.8082
Max Act: 6.3082. Min Act: -0.1700
Data Index: 6760726 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8082. Min Range: -6.8082
Max Act: 6.2769. Min Act: -0.1700
Data Index: 7031974 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8082. Min Range: -6.8082
Max Act: 6.1207. Min Act: -0.1700
Data Index: 7789323 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8082. Min Range: -6.8082
Max Act: 6.0894. Min Act: -0.1700
Data Index: 1029705 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8082. Min Range: -6.8082
Max Act: 6.0582. Min Act: -0.1700
Data Index: 146859 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8082. Min Range: -6.8082
Max Act: 6.0582. Min Act: -0.1700
Data Index: 1696931 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8082. Min Range: -6.8082
Max Act: 6.0582. Min Act: -0.1700
Data Index: 3998603 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8082. Min Range: -6.8082
Max Act: 6.0582. Min Act: -0.1700
Data Index: 4193252 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8082. Min Range: -6.8082
Max Act: 6.0269. Min Act: -0.1700
Data Index: 7016499 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8082. Min Range: -6.8082
Max Act: 5.9957. Min Act: -0.1700
Data Index: 1054370 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8082. Min Range: -6.8082
Max Act: 6.0269. Min Act: -0.1700
Data Index: 3501781 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8082. Min Range: -6.8082
Max Act: 5.9644. Min Act: -0.1700
Data Index: 6949395 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8082. Min Range: -6.8082
Max Act: 5.9644. Min Act: -0.1700
Data Index: 7148228 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8082. Min Range: -6.8082
Max Act: 5.9019. Min Act: -0.1700
Data Index: 5212842 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8082. Min Range: -6.8082
Max Act: 5.9019. Min Act: -0.1700
Data Index: 5342141 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8082. Min Range: -6.8082
Max Act: 5.9019. Min Act: -0.1700
Data Index: 7648438 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8082. Min Range: -6.8082
Max Act: 5.8707. Min Act: -0.1700
Data Index: 4185901 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19