Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1165 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.1123. Min Range: -3.1123
Max Act: 3.1123. Min Act: -0.1700
Data Index: 9302 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1123. Min Range: -3.1123
Max Act: 3.0807. Min Act: -0.1700
Data Index: 705743 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1123. Min Range: -3.1123
Max Act: 3.0807. Min Act: -0.1700
Data Index: 1328932 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1123. Min Range: -3.1123
Max Act: 3.0176. Min Act: -0.1700
Data Index: 513889 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1123. Min Range: -3.1123
Max Act: 3.0018. Min Act: -0.1700
Data Index: 82008 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1123. Min Range: -3.1123
Max Act: 3.0018. Min Act: -0.1700
Data Index: 315914 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9860. Min Act: -0.1700
Data Index: 1275295 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9860. Min Act: -0.1700
Data Index: 930646 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9860. Min Act: -0.1700
Data Index: 1300298 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9701. Min Act: -0.1700
Data Index: 232090 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9701. Min Act: -0.1700
Data Index: 119453 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9543. Min Act: -0.1700
Data Index: 855254 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9543. Min Act: -0.1700
Data Index: 1066920 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9543. Min Act: -0.1700
Data Index: 194018 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9543. Min Act: -0.1700
Data Index: 226497 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9385. Min Act: -0.1700
Data Index: 509522 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9385. Min Act: -0.1700
Data Index: 551267 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9385. Min Act: -0.1700
Data Index: 99522 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9226. Min Act: -0.1700
Data Index: 8305 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1123. Min Range: -3.1123
Max Act: 2.9226. Min Act: -0.1700
Data Index: 660397 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19