Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1968 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.6511. Min Act: -0.1700
Data Index: 21195 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.4636. Min Act: -0.1700
Data Index: 999824 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.4324. Min Act: -0.1700
Data Index: 1278581 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.4011. Min Act: -0.1700
Data Index: 1310646 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.3699. Min Act: -0.1698
Data Index: 647557 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.3386. Min Act: -0.1700
Data Index: 978804 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.3386. Min Act: -0.1700
Data Index: 1175830 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.3074. Min Act: -0.1700
Data Index: 521742 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.2761. Min Act: -0.1700
Data Index: 943528 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.1199. Min Act: -0.1700
Data Index: 1218921 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.2136. Min Act: -0.1699
Data Index: 129789 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.1824. Min Act: -0.1700
Data Index: 1179 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.2136. Min Act: -0.1700
Data Index: 379779 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.1199. Min Act: -0.1700
Data Index: 340221 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.1511. Min Act: -0.1700
Data Index: 69717 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.1511. Min Act: -0.1700
Data Index: 575325 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.1511. Min Act: -0.1700
Data Index: 937424 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.1199. Min Act: -0.1700
Data Index: 950087 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.0574. Min Act: -0.1699
Data Index: 436631 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6511. Min Range: -6.6511
Max Act: 6.0574. Min Act: -0.1700
Data Index: 923853 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19