Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5255 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.6650. Min Act: -0.1700
Data Index: 1857449 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.3525. Min Act: -0.1700
Data Index: 6584113 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.3525. Min Act: -0.1700
Data Index: 643281 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.1338. Min Act: -0.1700
Data Index: 1390751 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.1338. Min Act: -0.1700
Data Index: 5489634 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.1338. Min Act: -0.1700
Data Index: 4501402 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.1338. Min Act: -0.1700
Data Index: 5738618 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.1650. Min Act: -0.1700
Data Index: 4201152 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.1025. Min Act: -0.1700
Data Index: 2721717 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.1025. Min Act: -0.1700
Data Index: 638827 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.0713. Min Act: -0.1700
Data Index: 2862642 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.1025. Min Act: -0.1700
Data Index: 3715757 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.1025. Min Act: -0.1700
Data Index: 7512865 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.0713. Min Act: -0.1700
Data Index: 2196509 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6650. Min Range: -7.6650
Max Act: 6.9775. Min Act: -0.1700
Data Index: 2723457 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6650. Min Range: -7.6650
Max Act: 6.9775. Min Act: -0.1700
Data Index: 2267125 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6650. Min Range: -7.6650
Max Act: 7.0088. Min Act: -0.1700
Data Index: 1382962 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6650. Min Range: -7.6650
Max Act: 6.9775. Min Act: -0.1700
Data Index: 2091270 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6650. Min Range: -7.6650
Max Act: 6.9775. Min Act: -0.1700
Data Index: 4474396 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6650. Min Range: -7.6650
Max Act: 6.9775. Min Act: -0.1700
Data Index: 229288 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19