Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2015 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3521. Min Range: -4.3521
Max Act: 4.3521. Min Act: -0.1700
Data Index: 735250 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3521. Min Range: -4.3521
Max Act: 4.1645. Min Act: -0.1700
Data Index: 23019 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3521. Min Range: -4.3521
Max Act: 4.1020. Min Act: -0.1700
Data Index: 1232150 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3521. Min Range: -4.3521
Max Act: 4.1020. Min Act: -0.1700
Data Index: 433792 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3521. Min Range: -4.3521
Max Act: 4.1020. Min Act: -0.1700
Data Index: 1103125 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3521. Min Range: -4.3521
Max Act: 4.0707. Min Act: -0.1700
Data Index: 532521 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3521. Min Range: -4.3521
Max Act: 4.0395. Min Act: -0.1700
Data Index: 353923 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3521. Min Range: -4.3521
Max Act: 4.0707. Min Act: -0.1700
Data Index: 581471 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3521. Min Range: -4.3521
Max Act: 3.9457. Min Act: -0.1700
Data Index: 1165961 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3521. Min Range: -4.3521
Max Act: 3.9769. Min Act: -0.1700
Data Index: 1019315 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3521. Min Range: -4.3521
Max Act: 3.9769. Min Act: -0.1700
Data Index: 1132433 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3521. Min Range: -4.3521
Max Act: 3.9769. Min Act: -0.1700
Data Index: 842316 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3521. Min Range: -4.3521
Max Act: 4.0395. Min Act: -0.1700
Data Index: 1310279 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3521. Min Range: -4.3521
Max Act: 4.0395. Min Act: -0.1700
Data Index: 444944 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3521. Min Range: -4.3521
Max Act: 3.9457. Min Act: -0.1700
Data Index: 703626 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3521. Min Range: -4.3521
Max Act: 3.9457. Min Act: -0.1700
Data Index: 398412 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3521. Min Range: -4.3521
Max Act: 3.9769. Min Act: -0.1700
Data Index: 56910 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3521. Min Range: -4.3521
Max Act: 3.9457. Min Act: -0.1700
Data Index: 1133870 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3521. Min Range: -4.3521
Max Act: 3.9769. Min Act: -0.1700
Data Index: 955797 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3521. Min Range: -4.3521
Max Act: 3.9769. Min Act: -0.1700
Data Index: 1017550 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19