Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 305 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.0571. Min Range: -4.0571
Max Act: 4.0571. Min Act: -0.1700
Data Index: 251392 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.9789. Min Act: -0.1700
Data Index: 997973 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.8538. Min Act: -0.1700
Data Index: 1642989 (Python Code)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.7600. Min Act: -0.1700
Data Index: 1435253 (Python Code)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.7287. Min Act: -0.1700
Data Index: 173919 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.7443. Min Act: -0.1700
Data Index: 383909 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.6818. Min Act: -0.1700
Data Index: 437353 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.6505. Min Act: -0.1700
Data Index: 93955 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.6661. Min Act: -0.1700
Data Index: 594753 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.6818. Min Act: -0.1700
Data Index: 765643 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.6348. Min Act: -0.1700
Data Index: 846866 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.6505. Min Act: -0.1700
Data Index: 14488 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.5878. Min Act: -0.1700
Data Index: 1174014 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.6192. Min Act: -0.1700
Data Index: 1160682 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.6035. Min Act: -0.1700
Data Index: 1026616 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.5878. Min Act: -0.1700
Data Index: 757671 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.5878. Min Act: -0.1700
Data Index: 1202659 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.5722. Min Act: -0.1700
Data Index: 836998 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.5722. Min Act: -0.1700
Data Index: 431728 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0571. Min Range: -4.0571
Max Act: 3.5722. Min Act: -0.1700
Data Index: 519802 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19