Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4481 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2862. Min Range: -8.2862
Max Act: 8.2862. Min Act: -0.1700
Data Index: 4667221 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2862. Min Range: -8.2862
Max Act: 8.2862. Min Act: -0.1700
Data Index: 6834704 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2862. Min Range: -8.2862
Max Act: 8.2237. Min Act: -0.1700
Data Index: 4311074 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2862. Min Range: -8.2862
Max Act: 8.1612. Min Act: -0.1700
Data Index: 1512102 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2862. Min Range: -8.2862
Max Act: 8.1612. Min Act: -0.1700
Data Index: 3143170 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2862. Min Range: -8.2862
Max Act: 8.0987. Min Act: -0.1700
Data Index: 8665375 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2862. Min Range: -8.2862
Max Act: 8.0362. Min Act: -0.1700
Data Index: 2602007 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2862. Min Range: -8.2862
Max Act: 8.0362. Min Act: -0.1700
Data Index: 460815 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2862. Min Range: -8.2862
Max Act: 8.0362. Min Act: -0.1700
Data Index: 8455053 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2862. Min Range: -8.2862
Max Act: 7.9737. Min Act: -0.1700
Data Index: 441891 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2862. Min Range: -8.2862
Max Act: 7.9112. Min Act: -0.1700
Data Index: 8244727 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2862. Min Range: -8.2862
Max Act: 7.9112. Min Act: -0.1700
Data Index: 960103 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2862. Min Range: -8.2862
Max Act: 7.9112. Min Act: -0.1700
Data Index: 1788242 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2862. Min Range: -8.2862
Max Act: 7.9112. Min Act: -0.1700
Data Index: 2912987 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2862. Min Range: -8.2862
Max Act: 7.9112. Min Act: -0.1700
Data Index: 1322644 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2862. Min Range: -8.2862
Max Act: 7.8487. Min Act: -0.1700
Data Index: 7164970 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2862. Min Range: -8.2862
Max Act: 7.8487. Min Act: -0.1700
Data Index: 2605616 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2862. Min Range: -8.2862
Max Act: 7.8487. Min Act: -0.1700
Data Index: 3742445 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2862. Min Range: -8.2862
Max Act: 7.8487. Min Act: -0.1700
Data Index: 4900381 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2862. Min Range: -8.2862
Max Act: 7.8487. Min Act: -0.1700
Data Index: 1267212 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19