Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 85 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.5103. Min Act: -0.1700
Data Index: 304370 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.3853. Min Act: -0.1700
Data Index: 1185769 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.3853. Min Act: -0.1700
Data Index: 22717 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.3541. Min Act: -0.1700
Data Index: 174691 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.3853. Min Act: -0.1700
Data Index: 1201446 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.3228. Min Act: -0.1700
Data Index: 1105805 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.3853. Min Act: -0.1700
Data Index: 1008589 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.3228. Min Act: -0.1700
Data Index: 205014 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.3228. Min Act: -0.1700
Data Index: 58958 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.3228. Min Act: -0.1700
Data Index: 689913 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.2916. Min Act: -0.1700
Data Index: 9111 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.2603. Min Act: -0.1700
Data Index: 238640 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.3228. Min Act: -0.1700
Data Index: 1267056 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.2916. Min Act: -0.1700
Data Index: 44783 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.2603. Min Act: -0.1700
Data Index: 360729 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.2290. Min Act: -0.1700
Data Index: 723716 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.2290. Min Act: -0.1700
Data Index: 416350 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.2603. Min Act: -0.1700
Data Index: 575871 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.2603. Min Act: -0.1700
Data Index: 95545 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5103. Min Range: -4.5103
Max Act: 4.1978. Min Act: -0.1700
Data Index: 1241570 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19