Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1561 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.2314. Min Range: -5.2314
Max Act: 5.2314. Min Act: -0.1700
Data Index: 917863 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2314. Min Range: -5.2314
Max Act: 5.2314. Min Act: -0.1700
Data Index: 1406019 (Python Code)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2314. Min Range: -5.2314
Max Act: 5.1689. Min Act: -0.1700
Data Index: 87108 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2314. Min Range: -5.2314
Max Act: 5.2314. Min Act: -0.1700
Data Index: 1530326 (Python Code)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2314. Min Range: -5.2314
Max Act: 5.1689. Min Act: -0.1700
Data Index: 1208192 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2314. Min Range: -5.2314
Max Act: 5.1064. Min Act: -0.1700
Data Index: 1135800 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2314. Min Range: -5.2314
Max Act: 5.0439. Min Act: -0.1700
Data Index: 1609517 (Python Code)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2314. Min Range: -5.2314
Max Act: 5.1064. Min Act: -0.1700
Data Index: 691288 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2314. Min Range: -5.2314
Max Act: 5.1064. Min Act: -0.1700
Data Index: 193819 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2314. Min Range: -5.2314
Max Act: 5.0439. Min Act: -0.1700
Data Index: 1295537 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2314. Min Range: -5.2314
Max Act: 4.9814. Min Act: -0.1700
Data Index: 269275 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2314. Min Range: -5.2314
Max Act: 5.0126. Min Act: -0.1700
Data Index: 220563 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2314. Min Range: -5.2314
Max Act: 4.9814. Min Act: -0.1700
Data Index: 1089877 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2314. Min Range: -5.2314
Max Act: 4.9814. Min Act: -0.1700
Data Index: 420880 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2314. Min Range: -5.2314
Max Act: 4.8876. Min Act: -0.1700
Data Index: 1636984 (Python Code)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2314. Min Range: -5.2314
Max Act: 4.9814. Min Act: -0.1700
Data Index: 433229 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2314. Min Range: -5.2314
Max Act: 4.9501. Min Act: -0.1700
Data Index: 765352 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2314. Min Range: -5.2314
Max Act: 4.9501. Min Act: -0.1700
Data Index: 160070 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2314. Min Range: -5.2314
Max Act: 4.9189. Min Act: -0.1700
Data Index: 1169360 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2314. Min Range: -5.2314
Max Act: 4.9501. Min Act: -0.1700
Data Index: 45387 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19