Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 261 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.3180. Min Act: -0.1700
Data Index: 983001 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.2867. Min Act: -0.1700
Data Index: 992493 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.2242. Min Act: -0.1700
Data Index: 60447 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.1929. Min Act: -0.1700
Data Index: 155334 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.0991. Min Act: -0.1700
Data Index: 332259 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.1617. Min Act: -0.1700
Data Index: 820634 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.1304. Min Act: -0.1700
Data Index: 756281 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.0991. Min Act: -0.1700
Data Index: 362736 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.0679. Min Act: -0.1700
Data Index: 1213406 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.0366. Min Act: -0.1700
Data Index: 642317 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.0054. Min Act: -0.1700
Data Index: 1093876 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.0679. Min Act: -0.1700
Data Index: 856270 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.0991. Min Act: -0.1700
Data Index: 843868 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.0991. Min Act: -0.1700
Data Index: 1021098 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.0366. Min Act: -0.1700
Data Index: 1174858 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.0366. Min Act: -0.1700
Data Index: 1125587 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.0366. Min Act: -0.1700
Data Index: 294320 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.0054. Min Act: -0.1700
Data Index: 501651 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3180. Min Range: -4.3180
Max Act: 4.0366. Min Act: -0.1700
Data Index: 880858 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3180. Min Range: -4.3180
Max Act: 3.9741. Min Act: -0.1700
Data Index: 763615 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19