Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 65 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.8367. Min Act: -0.1700
Data Index: 474099 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.8049. Min Act: -0.1700
Data Index: 314083 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.8049. Min Act: -0.1700
Data Index: 623421 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.8367. Min Act: -0.1700
Data Index: 1005858 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.8208. Min Act: -0.1700
Data Index: 1213001 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7889. Min Act: -0.1700
Data Index: 1182275 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7889. Min Act: -0.1700
Data Index: 1141073 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7889. Min Act: -0.1700
Data Index: 918732 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7889. Min Act: -0.1700
Data Index: 1002656 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7730. Min Act: -0.1700
Data Index: 1127393 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7730. Min Act: -0.1700
Data Index: 1129432 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7570. Min Act: -0.1700
Data Index: 1199185 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7730. Min Act: -0.1700
Data Index: 697847 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7570. Min Act: -0.1700
Data Index: 158194 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7730. Min Act: -0.1700
Data Index: 295092 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7570. Min Act: -0.1700
Data Index: 1028487 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7730. Min Act: -0.1700
Data Index: 1109653 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7889. Min Act: -0.1700
Data Index: 547718 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7730. Min Act: -0.1700
Data Index: 239735 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8367. Min Range: -2.8367
Max Act: 2.7570. Min Act: -0.1700
Data Index: 552081 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19