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

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

Neuron 3458 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4186. Min Range: -2.4186

Max Act: 2.4186. Min Act: -0.0000

Data Index: 639588 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 2.4186. Min Range: -2.4186

Max Act: 2.3968. Min Act: -0.0000

Data Index: 58029 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 2.4186. Min Range: -2.4186

Max Act: 2.3142. Min Act: -0.0000

Data Index: 198603 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 2.4186. Min Range: -2.4186

Max Act: 2.2215. Min Act: -0.0000

Data Index: 485739 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 2.4186. Min Range: -2.4186

Max Act: 2.2119. Min Act: -0.0000

Data Index: 435100 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.9885. Min Act: -0.0000

Data Index: 715827 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.8673. Min Act: -0.0000

Data Index: 611054 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.9362. Min Act: -0.0000

Data Index: 429381 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.9249. Min Act: -0.0000

Data Index: 929843 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.8510. Min Act: -0.0000

Data Index: 1147423 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.8956. Min Act: -0.0000

Data Index: 513844 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.7456. Min Act: -0.0000

Data Index: 1156869 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.6432. Min Act: -0.0000

Data Index: 1295101 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.8328. Min Act: -0.0000

Data Index: 90923 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.7096. Min Act: -0.0000

Data Index: 1142764 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.7045. Min Act: -0.0000

Data Index: 247594 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.8041. Min Act: -0.0000

Data Index: 574007 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.6948. Min Act: -0.0000

Data Index: 1300252 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.6619. Min Act: -0.0000

Data Index: 290435 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 2.4186. Min Range: -2.4186

Max Act: 1.6307. Min Act: -0.0000

Data Index: 203669 (C4 (Web Text))

Max Activating Token Index: 748