Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1383 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 5.0353. Min Range: -5.0353
Max Act: 5.0353. Min Act: -0.1700
Data Index: 50943 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0353. Min Range: -5.0353
Max Act: 5.0040. Min Act: -0.1700
Data Index: 1052580 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9415. Min Act: -0.1700
Data Index: 442140 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9103. Min Act: -0.1700
Data Index: 547284 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8790. Min Act: -0.1700
Data Index: 1346208 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9103. Min Act: -0.1700
Data Index: 733185 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8790. Min Act: -0.1700
Data Index: 301520 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8790. Min Act: -0.1700
Data Index: 981579 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9415. Min Act: -0.1700
Data Index: 964079 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8165. Min Act: -0.1700
Data Index: 252125 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8478. Min Act: -0.1700
Data Index: 1016038 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9103. Min Act: -0.1700
Data Index: 500681 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9103. Min Act: -0.1700
Data Index: 1124576 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8165. Min Act: -0.1700
Data Index: 466735 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.7853. Min Act: -0.1700
Data Index: 925663 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.7853. Min Act: -0.1700
Data Index: 236503 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.7853. Min Act: -0.1700
Data Index: 311255 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8165. Min Act: -0.1700
Data Index: 540456 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8165. Min Act: -0.1700
Data Index: 172242 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.7540. Min Act: -0.1700
Data Index: 89468 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19