Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1371 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.7146. Min Act: -0.1700
Data Index: 310469 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.6834. Min Act: -0.1700
Data Index: 610527 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.5584. Min Act: -0.1700
Data Index: 476894 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.5584. Min Act: -0.1700
Data Index: 91781 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.4959. Min Act: -0.1700
Data Index: 231980 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.5271. Min Act: -0.1700
Data Index: 224658 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.5271. Min Act: -0.1700
Data Index: 1250124 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.5271. Min Act: -0.1700
Data Index: 249809 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.4959. Min Act: -0.1700
Data Index: 833865 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.4959. Min Act: -0.1700
Data Index: 451883 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.4959. Min Act: -0.1700
Data Index: 1324843 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.4646. Min Act: -0.1700
Data Index: 1213005 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.4646. Min Act: -0.1700
Data Index: 1133278 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.3865. Min Act: -0.1700
Data Index: 964545 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.4646. Min Act: -0.1700
Data Index: 650804 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.4959. Min Act: -0.1700
Data Index: 699344 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.4646. Min Act: -0.1700
Data Index: 789437 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.4646. Min Act: -0.1700
Data Index: 238333 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.4646. Min Act: -0.1700
Data Index: 903501 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7146. Min Range: -4.7146
Max Act: 4.4021. Min Act: -0.1700
Data Index: 643623 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19