Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.1597. Min Act: -0.1700
Data Index: 2728752 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.1597. Min Act: -0.1700
Data Index: 4697554 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.1284. Min Act: -0.1700
Data Index: 3902434 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.1284. Min Act: -0.1700
Data Index: 831236 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0972. Min Act: -0.1700
Data Index: 4490085 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0972. Min Act: -0.1700
Data Index: 7995261 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.1284. Min Act: -0.1700
Data Index: 2461878 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0972. Min Act: -0.1700
Data Index: 2085399 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0972. Min Act: -0.1700
Data Index: 8296185 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.1284. Min Act: -0.1700
Data Index: 7151625 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0972. Min Act: -0.1700
Data Index: 6471257 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0659. Min Act: -0.1700
Data Index: 4490083 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0659. Min Act: -0.1700
Data Index: 7254412 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0972. Min Act: -0.1700
Data Index: 3219636 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0659. Min Act: -0.1700
Data Index: 3194483 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0659. Min Act: -0.1700
Data Index: 4875929 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0659. Min Act: -0.1700
Data Index: 1885436 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0347. Min Act: -0.1700
Data Index: 7677280 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0034. Min Act: -0.1700
Data Index: 7001335 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1597. Min Range: -4.1597
Max Act: 4.0034. Min Act: -0.1700
Data Index: 4885115 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19