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

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

Neuron 1961 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.4777. Min Act: -0.0002

Data Index: 107659 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3980. Min Act: -0.0003

Data Index: 422661 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3972. Min Act: -0.0003

Data Index: 838989 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3794. Min Act: -0.0003

Data Index: 552711 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3757. Min Act: -0.0003

Data Index: 689351 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3685. Min Act: -0.0002

Data Index: 46068 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3648. Min Act: -0.0003

Data Index: 580573 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3612. Min Act: -0.0003

Data Index: 472258 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3471. Min Act: -0.0003

Data Index: 960982 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3549. Min Act: -0.0003

Data Index: 1047867 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3399. Min Act: -0.0003

Data Index: 946928 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3505. Min Act: -0.0002

Data Index: 939382 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3447. Min Act: -0.0003

Data Index: 1027186 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3429. Min Act: -0.0002

Data Index: 315751 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3326. Min Act: -0.0003

Data Index: 240908 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3322. Min Act: -0.0003

Data Index: 556857 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3318. Min Act: -0.0003

Data Index: 565873 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3298. Min Act: -0.0000

Data Index: 584499 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3277. Min Act: -0.0003

Data Index: 506312 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3272. Min Act: -0.0003

Data Index: 81050 (C4 (Web Text))

Max Activating Token Index: 703