Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 571 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4254. Min Range: -4.4254
Max Act: 4.4254. Min Act: -0.1700
Data Index: 11781 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4254. Min Range: -4.4254
Max Act: 4.2067. Min Act: -0.1700
Data Index: 69276 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4254. Min Range: -4.4254
Max Act: 4.1441. Min Act: -0.1700
Data Index: 1266833 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4254. Min Range: -4.4254
Max Act: 4.1129. Min Act: -0.1700
Data Index: 1191662 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4254. Min Range: -4.4254
Max Act: 4.1129. Min Act: -0.1700
Data Index: 24272 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4254. Min Range: -4.4254
Max Act: 4.0504. Min Act: -0.1700
Data Index: 1358499 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4254. Min Range: -4.4254
Max Act: 4.0504. Min Act: -0.1700
Data Index: 853742 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4254. Min Range: -4.4254
Max Act: 4.0191. Min Act: -0.1700
Data Index: 270269 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4254. Min Range: -4.4254
Max Act: 4.0504. Min Act: -0.1700
Data Index: 635905 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4254. Min Range: -4.4254
Max Act: 3.9253. Min Act: -0.1700
Data Index: 98254 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4254. Min Range: -4.4254
Max Act: 3.9878. Min Act: -0.1700
Data Index: 1008321 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4254. Min Range: -4.4254
Max Act: 3.9253. Min Act: -0.1700
Data Index: 511633 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4254. Min Range: -4.4254
Max Act: 3.8940. Min Act: -0.1700
Data Index: 614454 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4254. Min Range: -4.4254
Max Act: 3.9253. Min Act: -0.1700
Data Index: 720739 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4254. Min Range: -4.4254
Max Act: 3.8940. Min Act: -0.1700
Data Index: 139537 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4254. Min Range: -4.4254
Max Act: 3.8627. Min Act: -0.1700
Data Index: 758983 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4254. Min Range: -4.4254
Max Act: 3.8940. Min Act: -0.1700
Data Index: 833432 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4254. Min Range: -4.4254
Max Act: 3.8315. Min Act: -0.1700
Data Index: 1122183 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4254. Min Range: -4.4254
Max Act: 3.8940. Min Act: -0.1700
Data Index: 840080 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4254. Min Range: -4.4254
Max Act: 3.8002. Min Act: -0.1700
Data Index: 1208526 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19