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

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

Neuron 2982 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: 0.5183. Min Range: -0.5183

Max Act: 0.5183. Min Act: -0.0001

Data Index: 1128218 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4707. Min Act: -0.0000

Data Index: 220422 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4691. Min Act: -0.0000

Data Index: 924742 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1076916 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4659. Min Act: -0.0001

Data Index: 23506 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1041090 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4349. Min Act: -0.0001

Data Index: 265669 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4482. Min Act: -0.0000

Data Index: 785291 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4344. Min Act: -0.0001

Data Index: 1086052 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1286749 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4336. Min Act: -0.0000

Data Index: 712522 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4113. Min Act: -0.0001

Data Index: 453410 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4160. Min Act: -0.0000

Data Index: 874770 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1006676 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1310115 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4282. Min Act: -0.0000

Data Index: 189229 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3963. Min Act: -0.0001

Data Index: 122360 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1139000 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4085. Min Act: -0.0000

Data Index: 658574 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1268386 (C4 (Web Text))

Max Activating Token Index: 215