Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 384 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5631. Min Range: -9.5631
Max Act: 9.5631. Min Act: -0.1700
Data Index: 6803876 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5631. Min Range: -9.5631
Max Act: 9.3131. Min Act: -0.1700
Data Index: 6803877 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5631. Min Range: -9.5631
Max Act: 9.3756. Min Act: -0.1700
Data Index: 1177329 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5631. Min Range: -9.5631
Max Act: 9.1256. Min Act: -0.1700
Data Index: 581635 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5631. Min Range: -9.5631
Max Act: 9.1256. Min Act: -0.1700
Data Index: 4987147 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5631. Min Range: -9.5631
Max Act: 9.1256. Min Act: -0.1700
Data Index: 5847336 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5631. Min Range: -9.5631
Max Act: 9.0631. Min Act: -0.1700
Data Index: 936157 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5631. Min Range: -9.5631
Max Act: 8.9381. Min Act: -0.1700
Data Index: 4534243 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5631. Min Range: -9.5631
Max Act: 8.9381. Min Act: -0.1700
Data Index: 6838525 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5631. Min Range: -9.5631
Max Act: 8.8756. Min Act: -0.1700
Data Index: 7706790 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5631. Min Range: -9.5631
Max Act: 9.0006. Min Act: -0.1700
Data Index: 2888108 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5631. Min Range: -9.5631
Max Act: 8.9381. Min Act: -0.1700
Data Index: 1002864 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5631. Min Range: -9.5631
Max Act: 8.9381. Min Act: -0.1700
Data Index: 3832177 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5631. Min Range: -9.5631
Max Act: 8.9381. Min Act: -0.1700
Data Index: 4616705 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5631. Min Range: -9.5631
Max Act: 8.9381. Min Act: -0.1700
Data Index: 83234 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5631. Min Range: -9.5631
Max Act: 8.8756. Min Act: -0.1700
Data Index: 8300363 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5631. Min Range: -9.5631
Max Act: 8.8756. Min Act: -0.1700
Data Index: 3086304 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5631. Min Range: -9.5631
Max Act: 8.8756. Min Act: -0.1700
Data Index: 5382408 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5631. Min Range: -9.5631
Max Act: 8.8131. Min Act: -0.1700
Data Index: 1079330 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5631. Min Range: -9.5631
Max Act: 8.8756. Min Act: -0.1700
Data Index: 3264693 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19