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

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

Neuron 1076 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.5408. Min Act: -0.0003

Data Index: 645103 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4947. Min Act: -0.0003

Data Index: 119134 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4785. Min Act: -0.0003

Data Index: 256283 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4236. Min Act: -0.0003

Data Index: 696431 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4629. Min Act: -0.0003

Data Index: 1118361 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4552. Min Act: -0.0003

Data Index: 790449 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4380. Min Act: -0.0003

Data Index: 213710 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4378. Min Act: -0.0003

Data Index: 84574 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4285. Min Act: -0.0003

Data Index: 195542 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4415. Min Act: -0.0003

Data Index: 8028 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4373. Min Act: -0.0003

Data Index: 777381 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4543. Min Act: -0.0003

Data Index: 242303 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4193. Min Act: -0.0003

Data Index: 862775 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.3947. Min Act: -0.0003

Data Index: 424532 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4165. Min Act: -0.0003

Data Index: 409001 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.3991. Min Act: -0.0003

Data Index: 804556 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4119. Min Act: -0.0003

Data Index: 200336 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.3992. Min Act: -0.0003

Data Index: 620748 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4001. Min Act: -0.0003

Data Index: 425931 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.3978. Min Act: -0.0003

Data Index: 1103035 (C4 (Web Text))

Max Activating Token Index: 36