Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 66 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.9920. Min Act: -0.1700
Data Index: 1278108 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.9445. Min Act: -0.1700
Data Index: 62025 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.9445. Min Act: -0.1700
Data Index: 920122 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.9128. Min Act: -0.1700
Data Index: 219888 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8969. Min Act: -0.1700
Data Index: 1329049 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8969. Min Act: -0.1700
Data Index: 403375 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8652. Min Act: -0.1700
Data Index: 1207689 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8811. Min Act: -0.1700
Data Index: 823642 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8175. Min Act: -0.1700
Data Index: 439301 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8493. Min Act: -0.1700
Data Index: 799852 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8334. Min Act: -0.1700
Data Index: 1334377 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8493. Min Act: -0.1700
Data Index: 527956 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8334. Min Act: -0.1700
Data Index: 1221907 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8334. Min Act: -0.1700
Data Index: 534252 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8334. Min Act: -0.1700
Data Index: 1284415 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8016. Min Act: -0.1700
Data Index: 151654 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8175. Min Act: -0.1700
Data Index: 957294 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8493. Min Act: -0.1700
Data Index: 158657 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.7856. Min Act: -0.1700
Data Index: 1020847 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.7856. Min Act: -0.1700
Data Index: 766133 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19