Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1989 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.9370. Min Act: -0.1700
Data Index: 271410 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.5932. Min Act: -0.1700
Data Index: 1095401 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.6245. Min Act: -0.1700
Data Index: 348113 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.5620. Min Act: -0.1700
Data Index: 268553 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.4682. Min Act: -0.1700
Data Index: 1245279 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.5932. Min Act: -0.1700
Data Index: 1117814 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.4682. Min Act: -0.1700
Data Index: 1313857 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.3432. Min Act: -0.1700
Data Index: 1048261 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.2807. Min Act: -0.1700
Data Index: 76249 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.3120. Min Act: -0.1699
Data Index: 628379 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.3120. Min Act: -0.1700
Data Index: 883586 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.2807. Min Act: -0.1700
Data Index: 79478 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.3432. Min Act: -0.1700
Data Index: 1007435 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.3120. Min Act: -0.1700
Data Index: 217168 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.3745. Min Act: -0.1700
Data Index: 9516 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.2807. Min Act: -0.1700
Data Index: 837003 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.3432. Min Act: -0.1700
Data Index: 739607 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.3120. Min Act: -0.1700
Data Index: 355225 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.3120. Min Act: -0.1700
Data Index: 368575 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9370. Min Range: -4.9370
Max Act: 4.2807. Min Act: -0.1700
Data Index: 299995 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19