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

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

Neuron 2521 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2886. Min Act: -0.0000

Data Index: 13831 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.3107. Min Act: -0.0000

Data Index: 37375 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2980. Min Act: -0.0000

Data Index: 879364 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2884. Min Act: -0.0000

Data Index: 306977 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2792. Min Act: -0.0000

Data Index: 1046789 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2747. Min Act: -0.0000

Data Index: 178132 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2711. Min Act: -0.0000

Data Index: 51534 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2613. Min Act: -0.0000

Data Index: 280416 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1045401 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2669. Min Act: -0.0000

Data Index: 479308 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2598. Min Act: -0.0000

Data Index: 407448 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2657. Min Act: -0.0000

Data Index: 559077 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2614. Min Act: -0.0000

Data Index: 78546 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2364. Min Act: -0.0000

Data Index: 863764 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2464. Min Act: -0.0000

Data Index: 596003 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2402. Min Act: -0.0000

Data Index: 889271 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2548. Min Act: -0.0000

Data Index: 157459 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2308. Min Act: -0.0000

Data Index: 1239387 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2113. Min Act: -0.0000

Data Index: 887029 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2423. Min Act: -0.0000

Data Index: 112658 (C4 (Web Text))

Max Activating Token Index: 793