Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1354 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.9667. Min Act: -0.1700
Data Index: 703817 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.9033. Min Act: -0.1700
Data Index: 416848 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.8239. Min Act: -0.1700
Data Index: 900952 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.8080. Min Act: -0.1700
Data Index: 100074 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.8239. Min Act: -0.1700
Data Index: 1227506 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7921. Min Act: -0.1700
Data Index: 825127 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.8080. Min Act: -0.1700
Data Index: 716133 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7921. Min Act: -0.1700
Data Index: 980399 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7921. Min Act: -0.1700
Data Index: 593978 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7921. Min Act: -0.1700
Data Index: 332962 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7761. Min Act: -0.1700
Data Index: 1015331 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7602. Min Act: -0.1700
Data Index: 575354 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7602. Min Act: -0.1700
Data Index: 560363 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7761. Min Act: -0.1700
Data Index: 784796 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7602. Min Act: -0.1700
Data Index: 835287 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7442. Min Act: -0.1700
Data Index: 721205 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7442. Min Act: -0.1700
Data Index: 753441 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7282. Min Act: -0.1700
Data Index: 585973 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7282. Min Act: -0.1700
Data Index: 1198856 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9667. Min Range: -2.9667
Max Act: 2.7282. Min Act: -0.1700
Data Index: 759925 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19