Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2998 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.3123. Min Act: -0.0001

Data Index: 697109 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2272. Min Act: -0.0001

Data Index: 1582642 (Python Code)

Max Activating Token Index: 385

Text #2

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2468. Min Act: -0.0001

Data Index: 1604417 (Python Code)

Max Activating Token Index: 63

Text #3

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2517. Min Act: -0.0001

Data Index: 640178 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2450. Min Act: -0.0001

Data Index: 1565321 (Python Code)

Max Activating Token Index: 59

Text #5

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2382. Min Act: -0.0001

Data Index: 1138419 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2270. Min Act: -0.0001

Data Index: 1520981 (Python Code)

Max Activating Token Index: 419

Text #7

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2369. Min Act: -0.0001

Data Index: 1379344 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2262. Min Act: -0.0001

Data Index: 102111 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2455. Min Act: -0.0001

Data Index: 595756 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2381. Min Act: -0.0001

Data Index: 1594329 (Python Code)

Max Activating Token Index: 123

Text #11

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2322. Min Act: -0.0001

Data Index: 193775 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2312. Min Act: -0.0001

Data Index: 4803 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2155. Min Act: -0.0001

Data Index: 1431094 (Python Code)

Max Activating Token Index: 24

Text #14

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2152. Min Act: -0.0001

Data Index: 765992 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1978. Min Act: -0.0001

Data Index: 778294 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2004. Min Act: -0.0001

Data Index: 1330324 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1098318 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.1939. Min Act: -0.0001

Data Index: 1598413 (Python Code)

Max Activating Token Index: 344

Text #19

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2062. Min Act: -0.0001

Data Index: 944595 (C4 (Web Text))

Max Activating Token Index: 107