Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 60 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.9229. Min Act: -0.1700
Data Index: 1628669 (Python Code)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.8912. Min Act: -0.1700
Data Index: 31070 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.8277. Min Act: -0.1700
Data Index: 251749 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.8118. Min Act: -0.1700
Data Index: 500807 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7799. Min Act: -0.1700
Data Index: 411730 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7799. Min Act: -0.1700
Data Index: 558670 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7640. Min Act: -0.1700
Data Index: 1238105 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7640. Min Act: -0.1700
Data Index: 758014 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7640. Min Act: -0.1700
Data Index: 77125 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7320. Min Act: -0.1700
Data Index: 460826 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7640. Min Act: -0.1700
Data Index: 155895 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7480. Min Act: -0.1700
Data Index: 38919 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7320. Min Act: -0.1700
Data Index: 931422 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7480. Min Act: -0.1700
Data Index: 652384 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7480. Min Act: -0.1700
Data Index: 730589 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7320. Min Act: -0.1700
Data Index: 973884 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7480. Min Act: -0.1700
Data Index: 1004124 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7320. Min Act: -0.1700
Data Index: 1047945 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7320. Min Act: -0.1700
Data Index: 1105628 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9229. Min Range: -2.9229
Max Act: 2.7320. Min Act: -0.1700
Data Index: 722674 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19