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

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

Neuron 3345 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3363. Min Act: -0.0001

Data Index: 530983 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3461. Min Act: -0.0001

Data Index: 251332 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3358. Min Act: -0.0001

Data Index: 633007 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3242. Min Act: -0.0000

Data Index: 253341 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3212. Min Act: -0.0001

Data Index: 117278 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3293. Min Act: -0.0001

Data Index: 1097848 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3168. Min Act: -0.0001

Data Index: 143083 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2963. Min Act: -0.0001

Data Index: 599958 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3233. Min Act: -0.0001

Data Index: 1266839 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3005. Min Act: -0.0000

Data Index: 701905 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3032. Min Act: -0.0000

Data Index: 954795 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3148. Min Act: -0.0000

Data Index: 424685 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1200129 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2951. Min Act: -0.0001

Data Index: 136130 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3025. Min Act: -0.0001

Data Index: 271855 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2874. Min Act: -0.0001

Data Index: 121853 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2998. Min Act: -0.0000

Data Index: 102945 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2954. Min Act: -0.0000

Data Index: 636876 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3028. Min Act: -0.0001

Data Index: 649388 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2941. Min Act: -0.0000

Data Index: 122558 (C4 (Web Text))

Max Activating Token Index: 549