Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 127 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6940. Min Act: -0.1700
Data Index: 1187953 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.7100. Min Act: -0.1700
Data Index: 1010319 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6619. Min Act: -0.1700
Data Index: 27186 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6779. Min Act: -0.1700
Data Index: 847780 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6619. Min Act: -0.1700
Data Index: 518923 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6779. Min Act: -0.1700
Data Index: 1203154 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6619. Min Act: -0.1700
Data Index: 1503099 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6459. Min Act: -0.1700
Data Index: 963785 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6619. Min Act: -0.1700
Data Index: 145067 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6298. Min Act: -0.1700
Data Index: 58562 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6298. Min Act: -0.1700
Data Index: 83338 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6459. Min Act: -0.1700
Data Index: 795185 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6298. Min Act: -0.1700
Data Index: 536218 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6298. Min Act: -0.1700
Data Index: 1145790 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6137. Min Act: -0.1700
Data Index: 1414531 (Python Code)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.6298. Min Act: -0.1700
Data Index: 1400867 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.5816. Min Act: -0.1700
Data Index: 118104 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.5977. Min Act: -0.1700
Data Index: 1172790 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.5977. Min Act: -0.1700
Data Index: 67406 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7100. Min Range: -2.7100
Max Act: 2.5977. Min Act: -0.1700
Data Index: 703912 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19