Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 145 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.6941. Min Act: -0.1700
Data Index: 825066 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.6316. Min Act: -0.1700
Data Index: 1290036 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.4754. Min Act: -0.1700
Data Index: 879090 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.5691. Min Act: -0.1700
Data Index: 207604 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.5379. Min Act: -0.1700
Data Index: 321637 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.5066. Min Act: -0.1700
Data Index: 25088 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.5066. Min Act: -0.1700
Data Index: 784645 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.4441. Min Act: -0.1700
Data Index: 36890 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.4754. Min Act: -0.1700
Data Index: 699766 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.3816. Min Act: -0.1700
Data Index: 1054033 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.4441. Min Act: -0.1700
Data Index: 322207 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.3816. Min Act: -0.1700
Data Index: 516302 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.3816. Min Act: -0.1700
Data Index: 626579 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.4128. Min Act: -0.1700
Data Index: 263194 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.3816. Min Act: -0.1700
Data Index: 315019 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.3503. Min Act: -0.1700
Data Index: 447456 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.4128. Min Act: -0.1700
Data Index: 1273242 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.4128. Min Act: -0.1700
Data Index: 1116144 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.3503. Min Act: -0.1700
Data Index: 521212 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6941. Min Range: -4.6941
Max Act: 4.3191. Min Act: -0.1700
Data Index: 487821 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19