Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1084 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2900. Min Act: -0.0001

Data Index: 909703 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2848. Min Act: -0.0001

Data Index: 608838 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2588. Min Act: -0.0001

Data Index: 109028 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2061. Min Act: -0.0001

Data Index: 1059501 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2425. Min Act: -0.0001

Data Index: 173837 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2358. Min Act: -0.0001

Data Index: 519688 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2408. Min Act: -0.0001

Data Index: 1338827 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2253. Min Act: -0.0001

Data Index: 872652 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2296. Min Act: -0.0001

Data Index: 902729 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2186. Min Act: -0.0001

Data Index: 303330 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2214. Min Act: -0.0001

Data Index: 422841 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1275781 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2350. Min Act: -0.0001

Data Index: 102423 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2242. Min Act: -0.0001

Data Index: 241564 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2281. Min Act: -0.0001

Data Index: 371074 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2181. Min Act: -0.0001

Data Index: 161363 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2104. Min Act: -0.0001

Data Index: 528694 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2199. Min Act: -0.0001

Data Index: 950886 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1877. Min Act: -0.0001

Data Index: 399133 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2142. Min Act: -0.0001

Data Index: 125617 (C4 (Web Text))

Max Activating Token Index: 188