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

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

Neuron 508 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: 0.2825. Min Range: -0.2825

Max Act: 0.2825. Min Act: -0.0000

Data Index: 183208 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1363171 (Python Code)

Max Activating Token Index: 148

Text #2

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2309. Min Act: -0.0000

Data Index: 602239 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1077949 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2308. Min Act: -0.0001

Data Index: 756535 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2204. Min Act: -0.0000

Data Index: 105958 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2147. Min Act: -0.0001

Data Index: 110492 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2218. Min Act: -0.0000

Data Index: 730879 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2158. Min Act: -0.0000

Data Index: 275039 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2150. Min Act: -0.0000

Data Index: 989991 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2159. Min Act: -0.0000

Data Index: 175881 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2082. Min Act: -0.0000

Data Index: 544412 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1293522 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2080. Min Act: -0.0000

Data Index: 1180983 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2129. Min Act: -0.0001

Data Index: 406731 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2042. Min Act: -0.0000

Data Index: 291760 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2205. Min Act: -0.0000

Data Index: 87028 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1952. Min Act: -0.0000

Data Index: 245968 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2114. Min Act: -0.0000

Data Index: 190509 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2064. Min Act: -0.0000

Data Index: 804874 (C4 (Web Text))

Max Activating Token Index: 957