Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1712 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.0010. Min Range: -1.0010

Max Act: 1.0010. Min Act: -0.0002

Data Index: 270577 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.9307. Min Act: -0.0002

Data Index: 868150 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.9171. Min Act: -0.0002

Data Index: 872695 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7957. Min Act: -0.0002

Data Index: 267995 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.8186. Min Act: -0.0002

Data Index: 530087 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7995. Min Act: -0.0002

Data Index: 1353374 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7946. Min Act: -0.0002

Data Index: 654415 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.8117. Min Act: -0.0002

Data Index: 896470 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7737. Min Act: -0.0002

Data Index: 357299 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7481. Min Act: -0.0002

Data Index: 803724 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7432. Min Act: -0.0002

Data Index: 105898 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7350. Min Act: -0.0002

Data Index: 442925 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7404. Min Act: -0.0002

Data Index: 876593 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7459. Min Act: -0.0002

Data Index: 739060 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7251. Min Act: -0.0002

Data Index: 102133 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7297. Min Act: -0.0002

Data Index: 644761 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7325. Min Act: -0.0002

Data Index: 698829 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7385. Min Act: -0.0002

Data Index: 366933 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7279. Min Act: -0.0002

Data Index: 340051 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7310. Min Act: -0.0002

Data Index: 942313 (C4 (Web Text))

Max Activating Token Index: 325