Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1567 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.5665. Min Act: -0.0000

Data Index: 462158 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.4411. Min Act: -0.0000

Data Index: 405617 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.3094. Min Act: -0.0000

Data Index: 866304 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.2912. Min Act: 0.0000

Data Index: 611508 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.2936. Min Act: -0.0000

Data Index: 905574 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.2694. Min Act: -0.0000

Data Index: 234330 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.2477. Min Act: -0.0000

Data Index: 976381 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.2385. Min Act: -0.0000

Data Index: 526814 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.2249. Min Act: -0.0000

Data Index: 1202668 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.1418. Min Act: -0.0000

Data Index: 338134 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.0948. Min Act: -0.0000

Data Index: 1313820 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.1018. Min Act: -0.0000

Data Index: 497040 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.1922. Min Act: -0.0000

Data Index: 392462 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.1615. Min Act: -0.0000

Data Index: 880724 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.1237. Min Act: -0.0000

Data Index: 341852 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.0890. Min Act: -0.0000

Data Index: 114832 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.0891. Min Act: -0.0000

Data Index: 665305 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.0810. Min Act: -0.0000

Data Index: 932573 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1250946 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 1.5665. Min Range: -1.5665

Max Act: 1.0632. Min Act: 0.0000

Data Index: 1086096 (C4 (Web Text))

Max Activating Token Index: 171