Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 670 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1551. Min Range: -3.1551
Max Act: 3.1551. Min Act: -0.1700
Data Index: 605010 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1551. Min Range: -3.1551
Max Act: 3.0290. Min Act: -0.1700
Data Index: 532026 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9816. Min Act: -0.1700
Data Index: 1191498 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9974. Min Act: -0.1700
Data Index: 1031903 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1551. Min Range: -3.1551
Max Act: 3.0763. Min Act: -0.1700
Data Index: 920644 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9657. Min Act: -0.1700
Data Index: 1343148 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9974. Min Act: -0.1700
Data Index: 227692 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9816. Min Act: -0.1700
Data Index: 1206189 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9657. Min Act: -0.1700
Data Index: 1146816 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9499. Min Act: -0.1700
Data Index: 519387 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9499. Min Act: -0.1700
Data Index: 477240 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9816. Min Act: -0.1700
Data Index: 1259152 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9024. Min Act: -0.1700
Data Index: 683439 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9341. Min Act: -0.1700
Data Index: 1422093 (Python Code)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9341. Min Act: -0.1700
Data Index: 683588 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9499. Min Act: -0.1700
Data Index: 221787 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9974. Min Act: -0.1700
Data Index: 975491 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9657. Min Act: -0.1700
Data Index: 209907 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9182. Min Act: -0.1700
Data Index: 7909 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1551. Min Range: -3.1551
Max Act: 2.9341. Min Act: -0.1700
Data Index: 1096171 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19