Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2032 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.7888. Min Act: -0.1700
Data Index: 189955 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.7576. Min Act: -0.1700
Data Index: 780758 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.7576. Min Act: -0.1700
Data Index: 1157252 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.7263. Min Act: -0.1700
Data Index: 309842 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.7263. Min Act: -0.1700
Data Index: 319965 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.6638. Min Act: -0.1700
Data Index: 728224 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.6951. Min Act: -0.1700
Data Index: 1259529 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.6638. Min Act: -0.1700
Data Index: 533088 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.6951. Min Act: -0.1700
Data Index: 1213529 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.6326. Min Act: -0.1700
Data Index: 1075737 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.5701. Min Act: -0.1700
Data Index: 852329 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.5701. Min Act: -0.1700
Data Index: 169363 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.6013. Min Act: -0.1700
Data Index: 895477 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.5701. Min Act: -0.1700
Data Index: 89400 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.5701. Min Act: -0.1700
Data Index: 1056962 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.5076. Min Act: -0.1700
Data Index: 51694 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.5701. Min Act: -0.1700
Data Index: 1008677 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.5388. Min Act: -0.1700
Data Index: 801212 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.5388. Min Act: -0.1700
Data Index: 659643 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7888. Min Range: -4.7888
Max Act: 4.5076. Min Act: -0.1700
Data Index: 471814 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19