Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1032 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.6939. Min Act: -0.1700
Data Index: 4454025 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.6627. Min Act: -0.1700
Data Index: 3879812 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.4439. Min Act: -0.1700
Data Index: 5343042 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.3502. Min Act: -0.1700
Data Index: 1391376 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.4127. Min Act: -0.1700
Data Index: 4773623 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.2564. Min Act: -0.1700
Data Index: 5440036 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.1627. Min Act: -0.1700
Data Index: 382044 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.1627. Min Act: -0.1700
Data Index: 6136978 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.1627. Min Act: -0.1700
Data Index: 180082 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.1314. Min Act: -0.1700
Data Index: 6313555 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.1002. Min Act: -0.1700
Data Index: 7520419 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.0689. Min Act: -0.1700
Data Index: 6607940 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.0689. Min Act: -0.1700
Data Index: 8626928 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.0689. Min Act: -0.1700
Data Index: 200022 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.0689. Min Act: -0.1700
Data Index: 160779 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.0377. Min Act: -0.1700
Data Index: 7216279 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6939. Min Range: -7.6939
Max Act: 6.9752. Min Act: -0.1700
Data Index: 7877560 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6939. Min Range: -7.6939
Max Act: 6.9752. Min Act: -0.1700
Data Index: 8421739 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6939. Min Range: -7.6939
Max Act: 6.9752. Min Act: -0.1700
Data Index: 5962303 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6939. Min Range: -7.6939
Max Act: 6.9127. Min Act: -0.1700
Data Index: 1136467 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19