Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3723 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0463. Min Range: -6.0463
Max Act: 6.0463. Min Act: -0.1700
Data Index: 8626388 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.9213. Min Act: -0.1700
Data Index: 937601 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.7963. Min Act: -0.1700
Data Index: 6782830 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.7651. Min Act: -0.1700
Data Index: 1072110 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.7963. Min Act: -0.1700
Data Index: 591997 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.7338. Min Act: -0.1700
Data Index: 5659124 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.7338. Min Act: -0.1700
Data Index: 6053808 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.7026. Min Act: -0.1700
Data Index: 1760205 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.6401. Min Act: -0.1700
Data Index: 3389530 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.6401. Min Act: -0.1700
Data Index: 1376930 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.7026. Min Act: -0.1700
Data Index: 8001161 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.6088. Min Act: -0.1700
Data Index: 7112940 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.5463. Min Act: -0.1700
Data Index: 1744826 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.5151. Min Act: -0.1700
Data Index: 7443821 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.5463. Min Act: -0.1700
Data Index: 2270158 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.5151. Min Act: -0.1700
Data Index: 7327788 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.5151. Min Act: -0.1700
Data Index: 284035 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.3901. Min Act: -0.1700
Data Index: 117124 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.4838. Min Act: -0.1700
Data Index: 3870697 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0463. Min Range: -6.0463
Max Act: 5.4213. Min Act: -0.1700
Data Index: 7966962 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19