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

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

Neuron 1905 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: 0.4472. Min Range: -0.4472

Max Act: 0.4472. Min Act: -0.0001

Data Index: 869042 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1129608 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3617. Min Act: -0.0001

Data Index: 82547 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3432. Min Act: 0.0000

Data Index: 393705 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3425. Min Act: -0.0000

Data Index: 757631 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3278. Min Act: -0.0000

Data Index: 856323 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3490. Min Act: -0.0001

Data Index: 795970 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3326. Min Act: 0.0000

Data Index: 1167700 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3262. Min Act: -0.0001

Data Index: 1240434 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3247. Min Act: -0.0000

Data Index: 14121 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3212. Min Act: -0.0000

Data Index: 668602 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3202. Min Act: -0.0000

Data Index: 471808 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3154. Min Act: -0.0000

Data Index: 629881 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2986. Min Act: 0.0000

Data Index: 1095725 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3072. Min Act: 0.0000

Data Index: 158051 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3061. Min Act: -0.0000

Data Index: 42332 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1310964 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1023775 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3098. Min Act: -0.0001

Data Index: 580062 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3010. Min Act: -0.0001

Data Index: 171826 (C4 (Web Text))

Max Activating Token Index: 830