Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 38 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.5879. Min Act: -0.1700
Data Index: 168121 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.5879. Min Act: -0.1700
Data Index: 82100 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.5567. Min Act: -0.1700
Data Index: 94830 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.4942. Min Act: -0.1700
Data Index: 542018 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.4316. Min Act: -0.1700
Data Index: 1348016 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.4316. Min Act: -0.1700
Data Index: 657241 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.4316. Min Act: -0.1700
Data Index: 425481 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.3691. Min Act: -0.1700
Data Index: 1327007 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.3379. Min Act: -0.1700
Data Index: 404360 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.3379. Min Act: -0.1700
Data Index: 696541 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.3066. Min Act: -0.1700
Data Index: 85795 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.2754. Min Act: -0.1696
Data Index: 1287 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.2754. Min Act: -0.1700
Data Index: 1022228 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.2754. Min Act: -0.1700
Data Index: 447042 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.2754. Min Act: -0.1700
Data Index: 144341 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.2129. Min Act: -0.1691
Data Index: 260839 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.2129. Min Act: -0.1700
Data Index: 1353203 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.2441. Min Act: -0.1700
Data Index: 190118 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.2129. Min Act: -0.1700
Data Index: 1307945 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5879. Min Range: -4.5879
Max Act: 4.1816. Min Act: -0.1700
Data Index: 284661 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19