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

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

Neuron 2274 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: 0.4082. Min Range: -0.4082

Max Act: 0.4082. Min Act: -0.0001

Data Index: 2219 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3774. Min Act: -0.0000

Data Index: 103335 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3799. Min Act: -0.0000

Data Index: 418391 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3713. Min Act: -0.0000

Data Index: 322369 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3587. Min Act: -0.0000

Data Index: 334094 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1192821 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3660. Min Act: -0.0001

Data Index: 325847 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3424. Min Act: -0.0000

Data Index: 278499 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3638. Min Act: -0.0001

Data Index: 171868 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3115. Min Act: -0.0001

Data Index: 180663 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1303357 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1314331 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3255. Min Act: -0.0000

Data Index: 319068 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3303. Min Act: -0.0001

Data Index: 1255929 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3199. Min Act: 0.0000

Data Index: 645468 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3157. Min Act: -0.0001

Data Index: 429955 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1020462 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3123. Min Act: -0.0000

Data Index: 219005 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3054. Min Act: -0.0000

Data Index: 53105 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3002. Min Act: -0.0000

Data Index: 134542 (C4 (Web Text))

Max Activating Token Index: 114