Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1165 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.3325. Min Act: -0.1700
Data Index: 85894 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.3325. Min Act: -0.1700
Data Index: 199636 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1911. Min Act: -0.1700
Data Index: 339864 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1439. Min Act: -0.1700
Data Index: 1080575 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1596. Min Act: -0.1700
Data Index: 791868 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1439. Min Act: -0.1700
Data Index: 892729 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1596. Min Act: -0.1700
Data Index: 739275 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1596. Min Act: -0.1700
Data Index: 946471 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1596. Min Act: -0.1700
Data Index: 1035619 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1439. Min Act: -0.1700
Data Index: 679823 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1123. Min Act: -0.1700
Data Index: 1145793 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1439. Min Act: -0.1700
Data Index: 47588 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1281. Min Act: -0.1700
Data Index: 66772 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1123. Min Act: -0.1700
Data Index: 735498 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1123. Min Act: -0.1700
Data Index: 684347 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.0966. Min Act: -0.1700
Data Index: 497976 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1123. Min Act: -0.1700
Data Index: 283759 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.1281. Min Act: -0.1700
Data Index: 1069560 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.0808. Min Act: -0.1700
Data Index: 597213 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3325. Min Range: -3.3325
Max Act: 3.0966. Min Act: -0.1700
Data Index: 702363 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19