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

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

Neuron 5680 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.3366. Min Act: -0.0000

Data Index: 56309 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2619. Min Act: -0.0001

Data Index: 564248 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1336793 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2559. Min Act: -0.0001

Data Index: 293055 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2587. Min Act: -0.0001

Data Index: 297520 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2466. Min Act: -0.0001

Data Index: 761222 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2348. Min Act: -0.0000

Data Index: 728218 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2183. Min Act: -0.0001

Data Index: 550648 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1147350 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2265. Min Act: -0.0001

Data Index: 1081513 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2165. Min Act: -0.0001

Data Index: 1293540 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1211301 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2274. Min Act: -0.0001

Data Index: 1013393 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2258. Min Act: -0.0000

Data Index: 750496 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2223. Min Act: -0.0001

Data Index: 561934 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2347. Min Act: -0.0001

Data Index: 219179 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.1998. Min Act: -0.0001

Data Index: 962089 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1276508 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2266. Min Act: -0.0001

Data Index: 1331503 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2308. Min Act: -0.0001

Data Index: 343120 (C4 (Web Text))

Max Activating Token Index: 159