Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 29 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.1251. Min Act: -0.1700
Data Index: 11941 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0936. Min Act: -0.1700
Data Index: 26839 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0620. Min Act: -0.1700
Data Index: 266381 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0936. Min Act: -0.1700
Data Index: 638815 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0778. Min Act: -0.1700
Data Index: 1234006 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0620. Min Act: -0.1700
Data Index: 963075 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0620. Min Act: -0.1700
Data Index: 871201 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0620. Min Act: -0.1700
Data Index: 1182100 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0620. Min Act: -0.1700
Data Index: 97526 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0462. Min Act: -0.1700
Data Index: 1113765 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0462. Min Act: -0.1700
Data Index: 1210262 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0462. Min Act: -0.1700
Data Index: 828990 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0462. Min Act: -0.1700
Data Index: 216536 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0462. Min Act: -0.1700
Data Index: 736852 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0462. Min Act: -0.1700
Data Index: 628210 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0304. Min Act: -0.1700
Data Index: 661667 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0304. Min Act: -0.1700
Data Index: 1209554 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0304. Min Act: -0.1700
Data Index: 867171 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0304. Min Act: -0.1700
Data Index: 511316 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1251. Min Range: -3.1251
Max Act: 3.0304. Min Act: -0.1700
Data Index: 1001335 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19