Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9778. Min Act: -0.1700
Data Index: 163153 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9778. Min Act: -0.1700
Data Index: 898274 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9620. Min Act: -0.1700
Data Index: 975406 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9620. Min Act: -0.1700
Data Index: 426707 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9620. Min Act: -0.1700
Data Index: 939160 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9461. Min Act: -0.1700
Data Index: 489966 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9303. Min Act: -0.1700
Data Index: 471639 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9303. Min Act: -0.1700
Data Index: 855493 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9303. Min Act: -0.1700
Data Index: 1206995 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9144. Min Act: -0.1700
Data Index: 878201 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9144. Min Act: -0.1700
Data Index: 1240097 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9144. Min Act: -0.1700
Data Index: 1049808 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9144. Min Act: -0.1700
Data Index: 1220426 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9144. Min Act: -0.1700
Data Index: 263124 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9144. Min Act: -0.1700
Data Index: 1239873 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.9144. Min Act: -0.1700
Data Index: 206310 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.8986. Min Act: -0.1700
Data Index: 468951 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.8986. Min Act: -0.1700
Data Index: 83829 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.8986. Min Act: -0.1700
Data Index: 436186 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9778. Min Range: -2.9778
Max Act: 2.8986. Min Act: -0.1700
Data Index: 515213 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19