Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 708 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.2748. Min Act: -0.1700
Data Index: 132347 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.2436. Min Act: -0.1700
Data Index: 654944 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.2436. Min Act: -0.1700
Data Index: 1115178 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.1811. Min Act: -0.1700
Data Index: 1192768 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.1186. Min Act: -0.1700
Data Index: 666339 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.1811. Min Act: -0.1700
Data Index: 89547 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.1811. Min Act: -0.1700
Data Index: 887791 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0248. Min Act: -0.1700
Data Index: 936233 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0873. Min Act: -0.1700
Data Index: 170862 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.1811. Min Act: -0.1700
Data Index: 543968 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0873. Min Act: -0.1700
Data Index: 350686 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0248. Min Act: -0.1700
Data Index: 623526 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0560. Min Act: -0.1700
Data Index: 932469 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0873. Min Act: -0.1700
Data Index: 1006448 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0560. Min Act: -0.1700
Data Index: 324874 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2748. Min Range: -4.2748
Max Act: 3.9935. Min Act: -0.1700
Data Index: 1145751 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0873. Min Act: -0.1700
Data Index: 245998 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0873. Min Act: -0.1700
Data Index: 207835 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.1498. Min Act: -0.1700
Data Index: 810602 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0248. Min Act: -0.1700
Data Index: 901699 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19