Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1250 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.6222. Min Act: -0.1700
Data Index: 508217 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.5284. Min Act: -0.1700
Data Index: 990856 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.5597. Min Act: -0.1700
Data Index: 1097054 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4972. Min Act: -0.1700
Data Index: 354104 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.5284. Min Act: -0.1700
Data Index: 739005 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4972. Min Act: -0.1700
Data Index: 796193 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4659. Min Act: -0.1700
Data Index: 679976 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4972. Min Act: -0.1700
Data Index: 856328 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4972. Min Act: -0.1700
Data Index: 370058 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4972. Min Act: -0.1700
Data Index: 569787 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4972. Min Act: -0.1700
Data Index: 1224583 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4972. Min Act: -0.1700
Data Index: 1253776 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4659. Min Act: -0.1700
Data Index: 1351123 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4347. Min Act: -0.1700
Data Index: 537234 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4347. Min Act: -0.1700
Data Index: 1026831 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4659. Min Act: -0.1700
Data Index: 1040512 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4347. Min Act: -0.1700
Data Index: 662302 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4659. Min Act: -0.1700
Data Index: 666337 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4659. Min Act: -0.1700
Data Index: 468479 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6222. Min Range: -4.6222
Max Act: 4.4659. Min Act: -0.1700
Data Index: 674560 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19