Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3369 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8026. Min Range: -8.8026
Max Act: 8.8026. Min Act: -0.1700
Data Index: 7375001 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8026. Min Range: -8.8026
Max Act: 8.3026. Min Act: -0.1700
Data Index: 1188425 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8026. Min Range: -8.8026
Max Act: 8.2713. Min Act: -0.1700
Data Index: 3719993 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8026. Min Range: -8.8026
Max Act: 8.2401. Min Act: -0.1700
Data Index: 62740 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8026. Min Range: -8.8026
Max Act: 8.2401. Min Act: -0.1700
Data Index: 3196288 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8026. Min Range: -8.8026
Max Act: 8.1151. Min Act: -0.1700
Data Index: 3909366 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8026. Min Range: -8.8026
Max Act: 8.0838. Min Act: -0.1700
Data Index: 4704429 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8026. Min Range: -8.8026
Max Act: 8.0213. Min Act: -0.1700
Data Index: 1488813 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8026. Min Range: -8.8026
Max Act: 8.0213. Min Act: -0.1700
Data Index: 2505842 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8026. Min Range: -8.8026
Max Act: 7.9588. Min Act: -0.1700
Data Index: 7796288 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8026. Min Range: -8.8026
Max Act: 7.9588. Min Act: -0.1700
Data Index: 7160808 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8026. Min Range: -8.8026
Max Act: 7.9276. Min Act: -0.1700
Data Index: 3705267 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8026. Min Range: -8.8026
Max Act: 7.9276. Min Act: -0.1700
Data Index: 5359009 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8026. Min Range: -8.8026
Max Act: 7.8963. Min Act: -0.1700
Data Index: 6013760 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8026. Min Range: -8.8026
Max Act: 7.8338. Min Act: -0.1700
Data Index: 868405 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8026. Min Range: -8.8026
Max Act: 7.8338. Min Act: -0.1700
Data Index: 6788977 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8026. Min Range: -8.8026
Max Act: 7.8026. Min Act: -0.1700
Data Index: 5503141 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8026. Min Range: -8.8026
Max Act: 7.8026. Min Act: -0.1700
Data Index: 6685524 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8026. Min Range: -8.8026
Max Act: 7.7713. Min Act: -0.1700
Data Index: 1193146 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8026. Min Range: -8.8026
Max Act: 7.7713. Min Act: -0.1700
Data Index: 7724478 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19