Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4038 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2308. Min Range: -5.2308
Max Act: 5.2308. Min Act: -0.1700
Data Index: 2876188 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.9808. Min Act: -0.1700
Data Index: 1265213 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.9496. Min Act: -0.1700
Data Index: 692164 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.9183. Min Act: -0.1700
Data Index: 5790431 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.8246. Min Act: -0.1700
Data Index: 1410575 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.8246. Min Act: -0.1700
Data Index: 6076706 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.8558. Min Act: -0.1700
Data Index: 3655790 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7933. Min Act: -0.1700
Data Index: 6164799 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7621. Min Act: -0.1700
Data Index: 5283612 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7621. Min Act: -0.1700
Data Index: 38608 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7933. Min Act: -0.1700
Data Index: 7982764 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7933. Min Act: -0.1700
Data Index: 7758538 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7308. Min Act: -0.1700
Data Index: 2664520 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7308. Min Act: -0.1700
Data Index: 6968514 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7308. Min Act: -0.1700
Data Index: 4563462 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7308. Min Act: -0.1700
Data Index: 4222343 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7308. Min Act: -0.1700
Data Index: 8113020 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7308. Min Act: -0.1700
Data Index: 7145434 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7308. Min Act: -0.1700
Data Index: 6022126 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.6683. Min Act: -0.1700
Data Index: 4141262 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19