Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2046 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.8974. Min Act: -0.1700
Data Index: 1318865 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.8180. Min Act: -0.1700
Data Index: 1334718 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.8180. Min Act: -0.1700
Data Index: 1490659 (Python Code)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.8021. Min Act: -0.1700
Data Index: 1217362 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.8180. Min Act: -0.1700
Data Index: 677658 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.8180. Min Act: -0.1700
Data Index: 687783 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.7702. Min Act: -0.1700
Data Index: 512799 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.7702. Min Act: -0.1700
Data Index: 958011 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.7542. Min Act: -0.1700
Data Index: 1642937 (Python Code)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.7383. Min Act: -0.1700
Data Index: 1080724 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.7383. Min Act: -0.1700
Data Index: 1093910 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.7223. Min Act: -0.1700
Data Index: 479538 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.7223. Min Act: -0.1700
Data Index: 1308160 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.7383. Min Act: -0.1700
Data Index: 1267790 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.7223. Min Act: -0.1700
Data Index: 506659 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.7383. Min Act: -0.1700
Data Index: 281555 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.6903. Min Act: -0.1700
Data Index: 573537 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.7063. Min Act: -0.1700
Data Index: 1338387 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.7063. Min Act: -0.1700
Data Index: 907063 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8974. Min Range: -2.8974
Max Act: 2.6583. Min Act: -0.1700
Data Index: 1065521 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19