Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3184 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5859. Min Act: -0.0000

Data Index: 164247 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1060295 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5525. Min Act: -0.0000

Data Index: 324018 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5473. Min Act: -0.0000

Data Index: 390967 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5360. Min Act: -0.0000

Data Index: 714187 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4990. Min Act: -0.0000

Data Index: 78885 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4711. Min Act: -0.0000

Data Index: 30563 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4883. Min Act: -0.0000

Data Index: 204094 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5076. Min Act: -0.0000

Data Index: 817724 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4664. Min Act: -0.0000

Data Index: 71871 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4790. Min Act: -0.0000

Data Index: 50871 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1086041 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4680. Min Act: -0.0000

Data Index: 570927 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1047888 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1089243 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4463. Min Act: -0.0000

Data Index: 176440 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4245. Min Act: -0.0000

Data Index: 534992 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1361362 (Python Code)

Max Activating Token Index: 229

Text #18

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1008413 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4298. Min Act: -0.0000

Data Index: 469671 (C4 (Web Text))

Max Activating Token Index: 333