Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 823 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.7730. Min Act: -0.1700
Data Index: 208821 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.7570. Min Act: -0.1700
Data Index: 165482 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.7251. Min Act: -0.1700
Data Index: 270702 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.6931. Min Act: -0.1700
Data Index: 778705 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.7251. Min Act: -0.1700
Data Index: 1197633 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.7251. Min Act: -0.1700
Data Index: 625051 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.7251. Min Act: -0.1700
Data Index: 693880 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.7091. Min Act: -0.1700
Data Index: 232949 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.6931. Min Act: -0.1700
Data Index: 547334 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.6771. Min Act: -0.1700
Data Index: 70859 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.6931. Min Act: -0.1700
Data Index: 438493 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.6931. Min Act: -0.1700
Data Index: 707849 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.6931. Min Act: -0.1700
Data Index: 8882 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.6771. Min Act: -0.1700
Data Index: 236702 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.6771. Min Act: -0.1700
Data Index: 91495 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.6450. Min Act: -0.1700
Data Index: 438213 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.6611. Min Act: -0.1700
Data Index: 994598 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.6771. Min Act: -0.1700
Data Index: 1004170 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.6611. Min Act: -0.1700
Data Index: 602838 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7730. Min Range: -2.7730
Max Act: 2.6611. Min Act: -0.1700
Data Index: 520509 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19