Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1988 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3174. Min Range: -4.3174
Max Act: 4.3174. Min Act: -0.1700
Data Index: 110535 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3174. Min Range: -4.3174
Max Act: 4.1298. Min Act: -0.1700
Data Index: 471775 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3174. Min Range: -4.3174
Max Act: 4.0360. Min Act: -0.1700
Data Index: 117861 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3174. Min Range: -4.3174
Max Act: 4.0673. Min Act: -0.1700
Data Index: 876164 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.9735. Min Act: -0.1700
Data Index: 700618 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.9735. Min Act: -0.1700
Data Index: 276657 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.9735. Min Act: -0.1700
Data Index: 1245579 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.9422. Min Act: -0.1700
Data Index: 1353535 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.9422. Min Act: -0.1700
Data Index: 972175 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.9735. Min Act: -0.1700
Data Index: 552419 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.9422. Min Act: -0.1700
Data Index: 590100 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.9110. Min Act: -0.1700
Data Index: 452040 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.9110. Min Act: -0.1700
Data Index: 20986 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.8484. Min Act: -0.1700
Data Index: 1030041 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.9422. Min Act: -0.1700
Data Index: 119374 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.9110. Min Act: -0.1700
Data Index: 524182 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.8484. Min Act: -0.1700
Data Index: 271776 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.8797. Min Act: -0.1700
Data Index: 381510 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.8797. Min Act: -0.1700
Data Index: 168912 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3174. Min Range: -4.3174
Max Act: 3.8484. Min Act: -0.1700
Data Index: 596576 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19