Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1699 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.9979. Min Act: -0.1700
Data Index: 1250955 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.9979. Min Act: -0.1700
Data Index: 998771 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.9667. Min Act: -0.1700
Data Index: 274459 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.8417. Min Act: -0.1700
Data Index: 143462 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.8729. Min Act: -0.1700
Data Index: 1314853 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.8104. Min Act: -0.1700
Data Index: 534502 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.7792. Min Act: -0.1700
Data Index: 1034993 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.8104. Min Act: -0.1700
Data Index: 131419 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.8104. Min Act: -0.1700
Data Index: 1196461 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.7792. Min Act: -0.1700
Data Index: 70476 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.7792. Min Act: -0.1700
Data Index: 1280204 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.7479. Min Act: -0.1700
Data Index: 393263 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.7479. Min Act: -0.1700
Data Index: 552663 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.7479. Min Act: -0.1700
Data Index: 893580 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.7167. Min Act: -0.1700
Data Index: 138319 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.7479. Min Act: -0.1700
Data Index: 306738 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.6854. Min Act: -0.1700
Data Index: 514523 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.6542. Min Act: -0.1700
Data Index: 1058358 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.7167. Min Act: -0.1700
Data Index: 511536 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9979. Min Range: -4.9979
Max Act: 4.6854. Min Act: -0.1700
Data Index: 435615 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19