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

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

Neuron 1647 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2956. Min Act: -0.0001

Data Index: 720215 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2777. Min Act: -0.0001

Data Index: 1036369 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2760. Min Act: -0.0001

Data Index: 977562 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2688. Min Act: -0.0001

Data Index: 795121 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2591. Min Act: -0.0001

Data Index: 1118506 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2553. Min Act: -0.0001

Data Index: 824993 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2351. Min Act: -0.0001

Data Index: 913192 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2416. Min Act: -0.0001

Data Index: 663408 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2305. Min Act: -0.0001

Data Index: 85173 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2303. Min Act: -0.0001

Data Index: 1078239 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2276. Min Act: -0.0001

Data Index: 199482 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2099. Min Act: -0.0001

Data Index: 323130 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2169. Min Act: -0.0001

Data Index: 1245363 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2171. Min Act: -0.0001

Data Index: 1127271 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2154. Min Act: -0.0000

Data Index: 105264 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2217. Min Act: -0.0001

Data Index: 860785 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2194. Min Act: -0.0001

Data Index: 64068 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2121. Min Act: -0.0001

Data Index: 925896 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2190. Min Act: -0.0001

Data Index: 505883 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2178. Min Act: -0.0001

Data Index: 432532 (C4 (Web Text))

Max Activating Token Index: 164