Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1479 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.9276. Min Act: -0.1700
Data Index: 3780097 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.8964. Min Act: -0.1700
Data Index: 425893 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.8651. Min Act: -0.1700
Data Index: 206215 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.7401. Min Act: -0.1700
Data Index: 4203015 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.7401. Min Act: -0.1700
Data Index: 1152222 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.7089. Min Act: -0.1700
Data Index: 6843048 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.7089. Min Act: -0.1700
Data Index: 6189437 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.5839. Min Act: -0.1700
Data Index: 1821002 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.4901. Min Act: -0.1700
Data Index: 5298919 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.5526. Min Act: -0.1700
Data Index: 5098396 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.5214. Min Act: -0.1700
Data Index: 2415048 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.5214. Min Act: -0.1700
Data Index: 6189438 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.5214. Min Act: -0.1700
Data Index: 4573086 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.4589. Min Act: -0.1700
Data Index: 809000 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.5214. Min Act: -0.1700
Data Index: 6226780 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.5214. Min Act: -0.1700
Data Index: 614205 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.4901. Min Act: -0.1700
Data Index: 2113526 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.4901. Min Act: -0.1700
Data Index: 6504529 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.4589. Min Act: -0.1700
Data Index: 970740 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9276. Min Range: -5.9276
Max Act: 5.4589. Min Act: -0.1700
Data Index: 7338403 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19