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

Dataset: The Pile

Neuron 685 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1391618 (The Pile)

Max Activating Token Index: 70

Text #1

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1438157 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1195305 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4996. Min Act: -0.0000

Data Index: 673543 (The Pile)

Max Activating Token Index: 611

Text #4

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1280528 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1934788 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1362400 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1031382 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4605. Min Act: -0.0000

Data Index: 178469 (The Pile)

Max Activating Token Index: 122

Text #9

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4093. Min Act: -0.0001

Data Index: 1560193 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4414. Min Act: -0.0000

Data Index: 726301 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4171. Min Act: -0.0000

Data Index: 266522 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1652734 (The Pile)

Max Activating Token Index: 192

Text #13

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3523. Min Act: -0.0000

Data Index: 387061 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3950. Min Act: -0.0000

Data Index: 409896 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1211547 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1380174 (The Pile)

Max Activating Token Index: 838

Text #17

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3993. Min Act: -0.0000

Data Index: 131735 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3837. Min Act: -0.0000

Data Index: 195088 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1885082 (The Pile)

Max Activating Token Index: 863