Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4192 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.7825. Min Act: -0.1700
Data Index: 2156114 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.7512. Min Act: -0.1700
Data Index: 8452410 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.7200. Min Act: -0.1700
Data Index: 3929809 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.7200. Min Act: -0.1700
Data Index: 3301950 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6575. Min Act: -0.1700
Data Index: 1395452 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6887. Min Act: -0.1700
Data Index: 7291679 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6887. Min Act: -0.1700
Data Index: 7697825 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6575. Min Act: -0.1700
Data Index: 7210110 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6575. Min Act: -0.1700
Data Index: 6286358 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6575. Min Act: -0.1700
Data Index: 1019953 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6575. Min Act: -0.1700
Data Index: 8713080 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6262. Min Act: -0.1700
Data Index: 2823092 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6262. Min Act: -0.1700
Data Index: 2459316 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6262. Min Act: -0.1700
Data Index: 4859036 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6262. Min Act: -0.1700
Data Index: 488579 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6262. Min Act: -0.1700
Data Index: 1141334 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6262. Min Act: -0.1700
Data Index: 6121111 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6262. Min Act: -0.1700
Data Index: 7430086 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6262. Min Act: -0.1700
Data Index: 7467136 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7825. Min Range: -5.7825
Max Act: 5.6262. Min Act: -0.1700
Data Index: 3434808 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19