Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1497 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.6499. Min Act: -0.1700
Data Index: 1056918 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.5090. Min Act: -0.1700
Data Index: 1198092 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.5246. Min Act: -0.1700
Data Index: 394926 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.5246. Min Act: -0.1700
Data Index: 497482 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.5403. Min Act: -0.1700
Data Index: 370787 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.5090. Min Act: -0.1700
Data Index: 452970 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.4619. Min Act: -0.1700
Data Index: 405149 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.4619. Min Act: -0.1700
Data Index: 590558 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.4619. Min Act: -0.1700
Data Index: 509788 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.4619. Min Act: -0.1700
Data Index: 194743 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.4619. Min Act: -0.1700
Data Index: 405304 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.4463. Min Act: -0.1700
Data Index: 1344418 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.4776. Min Act: -0.1700
Data Index: 469062 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.4463. Min Act: -0.1700
Data Index: 1102541 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.4463. Min Act: -0.1700
Data Index: 273789 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.4463. Min Act: -0.1700
Data Index: 1150274 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.4619. Min Act: -0.1700
Data Index: 725603 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.4463. Min Act: -0.1700
Data Index: 218683 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.4463. Min Act: -0.1700
Data Index: 617167 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6499. Min Range: -3.6499
Max Act: 3.3992. Min Act: -0.1700
Data Index: 397478 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19