Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1961 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3925. Min Act: -0.0000

Data Index: 230298 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2996. Min Act: -0.0000

Data Index: 338304 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2659. Min Act: -0.0000

Data Index: 163655 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2958. Min Act: -0.0000

Data Index: 209496 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2671. Min Act: -0.0000

Data Index: 797362 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2689. Min Act: -0.0001

Data Index: 965261 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2456. Min Act: -0.0000

Data Index: 403587 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2460. Min Act: -0.0001

Data Index: 514912 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2367. Min Act: -0.0000

Data Index: 169328 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2530. Min Act: 0.0000

Data Index: 169161 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2374. Min Act: -0.0000

Data Index: 524655 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2336. Min Act: -0.0000

Data Index: 137843 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2411. Min Act: -0.0000

Data Index: 97829 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1006561 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1207856 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2186. Min Act: -0.0001

Data Index: 1153870 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2308. Min Act: -0.0000

Data Index: 891941 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2146. Min Act: -0.0000

Data Index: 1284618 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2224. Min Act: -0.0000

Data Index: 434849 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2197. Min Act: -0.0000

Data Index: 420282 (C4 (Web Text))

Max Activating Token Index: 121