Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 137 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3004. Min Range: -8.3004
Max Act: 8.3004. Min Act: -0.1700
Data Index: 5799551 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3004. Min Range: -8.3004
Max Act: 7.9254. Min Act: -0.1700
Data Index: 3680935 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3004. Min Range: -8.3004
Max Act: 7.6442. Min Act: -0.1700
Data Index: 7536174 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3004. Min Range: -8.3004
Max Act: 7.1442. Min Act: -0.1700
Data Index: 4818221 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3004. Min Range: -8.3004
Max Act: 7.1442. Min Act: -0.1700
Data Index: 228383 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3004. Min Range: -8.3004
Max Act: 7.1442. Min Act: -0.1700
Data Index: 5322853 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3004. Min Range: -8.3004
Max Act: 7.0817. Min Act: -0.1700
Data Index: 3240158 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3004. Min Range: -8.3004
Max Act: 7.0817. Min Act: -0.1700
Data Index: 7840051 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3004. Min Range: -8.3004
Max Act: 7.0817. Min Act: -0.1700
Data Index: 3536970 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3004. Min Range: -8.3004
Max Act: 7.0504. Min Act: -0.1700
Data Index: 7206570 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3004. Min Range: -8.3004
Max Act: 6.9879. Min Act: -0.1700
Data Index: 4664858 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3004. Min Range: -8.3004
Max Act: 6.9879. Min Act: -0.1700
Data Index: 1470434 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3004. Min Range: -8.3004
Max Act: 6.9567. Min Act: -0.1700
Data Index: 339722 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3004. Min Range: -8.3004
Max Act: 6.9567. Min Act: -0.1700
Data Index: 8768992 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3004. Min Range: -8.3004
Max Act: 6.9567. Min Act: -0.1700
Data Index: 913964 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3004. Min Range: -8.3004
Max Act: 6.9254. Min Act: -0.1700
Data Index: 1206799 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3004. Min Range: -8.3004
Max Act: 6.9254. Min Act: -0.1700
Data Index: 3466433 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3004. Min Range: -8.3004
Max Act: 6.8942. Min Act: -0.1700
Data Index: 2357009 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3004. Min Range: -8.3004
Max Act: 6.8942. Min Act: -0.1700
Data Index: 5785293 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3004. Min Range: -8.3004
Max Act: 6.8942. Min Act: -0.1700
Data Index: 4973214 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19