Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 512 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0015. Min Range: -3.0015
Max Act: 3.0015. Min Act: -0.1700
Data Index: 794805 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.9540. Min Act: -0.1700
Data Index: 636551 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.9540. Min Act: -0.1700
Data Index: 41713 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.9382. Min Act: -0.1700
Data Index: 979058 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.9382. Min Act: -0.1700
Data Index: 462195 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.9065. Min Act: -0.1700
Data Index: 1141165 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.9065. Min Act: -0.1700
Data Index: 1015410 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.8747. Min Act: -0.1700
Data Index: 472699 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.8747. Min Act: -0.1700
Data Index: 1330079 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.8906. Min Act: -0.1700
Data Index: 1228003 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.8747. Min Act: -0.1700
Data Index: 73443 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.8747. Min Act: -0.1700
Data Index: 1178180 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.8747. Min Act: -0.1700
Data Index: 234654 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.8429. Min Act: -0.1700
Data Index: 1210450 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.8588. Min Act: -0.1700
Data Index: 1170366 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.8588. Min Act: -0.1700
Data Index: 241459 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.8588. Min Act: -0.1700
Data Index: 266053 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.8429. Min Act: -0.1700
Data Index: 1052009 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.8270. Min Act: -0.1700
Data Index: 1061777 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0015. Min Range: -3.0015
Max Act: 2.8111. Min Act: -0.1700
Data Index: 3663 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19