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

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

Neuron 3960 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: 0.2934. Min Range: -0.2934

Max Act: 0.2934. Min Act: -0.0001

Data Index: 498190 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2815. Min Act: -0.0001

Data Index: 618606 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2689. Min Act: -0.0001

Data Index: 267154 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2583. Min Act: -0.0000

Data Index: 345310 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2575. Min Act: -0.0000

Data Index: 932417 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2294. Min Act: -0.0001

Data Index: 581766 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2641. Min Act: -0.0001

Data Index: 134300 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2489. Min Act: -0.0000

Data Index: 438288 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1214815 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2200. Min Act: -0.0000

Data Index: 102679 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1206665 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2445. Min Act: -0.0000

Data Index: 451685 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2128. Min Act: -0.0000

Data Index: 292448 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2332. Min Act: -0.0001

Data Index: 206357 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2216. Min Act: -0.0000

Data Index: 591 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2249. Min Act: -0.0000

Data Index: 421811 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2177. Min Act: -0.0001

Data Index: 937933 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2264. Min Act: -0.0001

Data Index: 420747 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2152. Min Act: -0.0000

Data Index: 851840 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2224. Min Act: -0.0001

Data Index: 629805 (C4 (Web Text))

Max Activating Token Index: 126