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

Dataset: The Pile

Neuron 1015 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.6360. Min Act: -0.0000

Data Index: 251419 (The Pile)

Max Activating Token Index: 242

Text #1

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.6183. Min Act: -0.0000

Data Index: 1370218 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.6985. Min Act: -0.0000

Data Index: 1000152 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.7692. Min Act: -0.0000

Data Index: 421935 (The Pile)

Max Activating Token Index: 970

Text #4

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.4546. Min Act: -0.0000

Data Index: 1654040 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.4167. Min Act: -0.0000

Data Index: 648991 (The Pile)

Max Activating Token Index: 364

Text #6

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.4158. Min Act: -0.0000

Data Index: 624035 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.4639. Min Act: -0.0000

Data Index: 360161 (The Pile)

Max Activating Token Index: 773

Text #8

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.5242. Min Act: -0.0000

Data Index: 306252 (The Pile)

Max Activating Token Index: 587

Text #9

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.4244. Min Act: -0.0000

Data Index: 1259535 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.4163. Min Act: -0.0000

Data Index: 76068 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.3458. Min Act: -0.0000

Data Index: 1257112 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.3045. Min Act: -0.0000

Data Index: 700988 (The Pile)

Max Activating Token Index: 983

Text #13

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.4033. Min Act: -0.0000

Data Index: 714984 (The Pile)

Max Activating Token Index: 849

Text #14

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.2662. Min Act: -0.0000

Data Index: 198741 (The Pile)

Max Activating Token Index: 226

Text #15

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1104240 (The Pile)

Max Activating Token Index: 226

Text #16

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.2259. Min Act: -0.0000

Data Index: 171845 (The Pile)

Max Activating Token Index: 634

Text #17

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.3136. Min Act: -0.0000

Data Index: 479970 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1319030 (The Pile)

Max Activating Token Index: 485

Text #19

Max Range: 1.7692. Min Range: -1.7692

Max Act: 1.2325. Min Act: -0.0000

Data Index: 1625026 (The Pile)

Max Activating Token Index: 239