Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4950 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.6616. Min Act: -0.1700
Data Index: 6200546 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.5678. Min Act: -0.1700
Data Index: 2468935 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.5366. Min Act: -0.1700
Data Index: 6036867 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.5053. Min Act: -0.1700
Data Index: 1503619 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4741. Min Act: -0.1700
Data Index: 893851 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4741. Min Act: -0.1700
Data Index: 8191290 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4428. Min Act: -0.1700
Data Index: 2892364 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4116. Min Act: -0.1700
Data Index: 593826 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4428. Min Act: -0.1700
Data Index: 7357199 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4116. Min Act: -0.1700
Data Index: 4735528 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4116. Min Act: -0.1700
Data Index: 5810036 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4116. Min Act: -0.1700
Data Index: 8028 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.3803. Min Act: -0.1700
Data Index: 6036869 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.3803. Min Act: -0.1700
Data Index: 8362094 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4116. Min Act: -0.1700
Data Index: 3578135 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.3803. Min Act: -0.1700
Data Index: 3586344 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.3803. Min Act: -0.1700
Data Index: 6544207 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.3491. Min Act: -0.1700
Data Index: 3396275 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.3491. Min Act: -0.1700
Data Index: 6268538 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.3491. Min Act: -0.1700
Data Index: 6421303 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19