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

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

Neuron 963 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.1963. Min Act: -0.0003

Data Index: 937745 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0577. Min Act: -0.0003

Data Index: 252622 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0619. Min Act: -0.0003

Data Index: 691807 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0922. Min Act: -0.0003

Data Index: 1318555 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0209. Min Act: -0.0003

Data Index: 465358 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.1272. Min Act: -0.0003

Data Index: 1334459 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.9309. Min Act: -0.0003

Data Index: 1295822 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.9038. Min Act: -0.0003

Data Index: 106081 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.9263. Min Act: -0.0003

Data Index: 458379 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 1.1963. Min Range: -1.1963

Max Act: 1.0721. Min Act: -0.0003

Data Index: 1311865 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.8930. Min Act: -0.0003

Data Index: 215438 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.8453. Min Act: -0.0003

Data Index: 33565 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.8994. Min Act: -0.0003

Data Index: 652863 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.8628. Min Act: -0.0003

Data Index: 694632 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.9130. Min Act: -0.0003

Data Index: 255673 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.8709. Min Act: -0.0003

Data Index: 1163708 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.8576. Min Act: -0.0003

Data Index: 643572 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.8705. Min Act: -0.0003

Data Index: 838923 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.8134. Min Act: -0.0003

Data Index: 103674 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.1963. Min Range: -1.1963

Max Act: 0.8070. Min Act: -0.0003

Data Index: 1209334 (C4 (Web Text))

Max Activating Token Index: 29