Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1350 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 5.1806. Min Range: -5.1806
Max Act: 5.1806. Min Act: -0.1700
Data Index: 1206998 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.9931. Min Act: -0.1700
Data Index: 665394 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1806. Min Range: -5.1806
Max Act: 5.0244. Min Act: -0.1700
Data Index: 56528 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.8681. Min Act: -0.1700
Data Index: 677462 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.7744. Min Act: -0.1700
Data Index: 705469 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.8369. Min Act: -0.1700
Data Index: 491083 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.8369. Min Act: -0.1700
Data Index: 315065 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.7118. Min Act: -0.1700
Data Index: 703736 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.7118. Min Act: -0.1700
Data Index: 173343 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.7118. Min Act: -0.1700
Data Index: 968740 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.7431. Min Act: -0.1700
Data Index: 95741 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.7118. Min Act: -0.1700
Data Index: 240679 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.6806. Min Act: -0.1700
Data Index: 6409 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.5868. Min Act: -0.1700
Data Index: 933169 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.6806. Min Act: -0.1700
Data Index: 1139616 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.6493. Min Act: -0.1700
Data Index: 121388 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.6181. Min Act: -0.1700
Data Index: 220929 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.6806. Min Act: -0.1700
Data Index: 868927 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.6181. Min Act: -0.1700
Data Index: 161455 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1806. Min Range: -5.1806
Max Act: 4.5868. Min Act: -0.1700
Data Index: 1065889 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19