Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 57 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.9305. Min Act: -0.1700
Data Index: 527866 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.9146. Min Act: -0.1700
Data Index: 1184444 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.9146. Min Act: -0.1700
Data Index: 236021 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.8988. Min Act: -0.1700
Data Index: 99565 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.8670. Min Act: -0.1700
Data Index: 231484 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.8829. Min Act: -0.1700
Data Index: 1301167 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.8829. Min Act: -0.1700
Data Index: 1150941 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.8353. Min Act: -0.1700
Data Index: 440973 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.8512. Min Act: -0.1700
Data Index: 259290 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.8193. Min Act: -0.1700
Data Index: 1000110 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.8193. Min Act: -0.1700
Data Index: 957857 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.8193. Min Act: -0.1700
Data Index: 300913 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.8034. Min Act: -0.1700
Data Index: 1325317 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.8193. Min Act: -0.1700
Data Index: 27517 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.7716. Min Act: -0.1700
Data Index: 1333749 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.7716. Min Act: -0.1700
Data Index: 1143802 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.7716. Min Act: -0.1700
Data Index: 1357013 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.7716. Min Act: -0.1700
Data Index: 1088795 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.7556. Min Act: -0.1700
Data Index: 654970 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9305. Min Range: -2.9305
Max Act: 2.7237. Min Act: -0.1700
Data Index: 1080644 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19