Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2824 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.5827. Min Act: -0.0000

Data Index: 1587684 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.6381. Min Act: -0.0000

Data Index: 751576 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.7152. Min Act: -0.0000

Data Index: 878731 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.9166. Min Act: -0.0000

Data Index: 107908 (The Pile)

Max Activating Token Index: 224

Text #4

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.5465. Min Act: -0.0000

Data Index: 796435 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.5485. Min Act: -0.0000

Data Index: 1344416 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.4455. Min Act: -0.0000

Data Index: 214508 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.3064. Min Act: -0.0000

Data Index: 238593 (The Pile)

Max Activating Token Index: 889

Text #8

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.4465. Min Act: -0.0000

Data Index: 68705 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.5155. Min Act: -0.0000

Data Index: 931014 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.5090. Min Act: -0.0000

Data Index: 794648 (The Pile)

Max Activating Token Index: 927

Text #11

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.3521. Min Act: -0.0000

Data Index: 1937375 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.4296. Min Act: -0.0000

Data Index: 1519160 (The Pile)

Max Activating Token Index: 388

Text #13

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.4289. Min Act: -0.0000

Data Index: 713438 (The Pile)

Max Activating Token Index: 860

Text #14

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.4098. Min Act: -0.0000

Data Index: 759490 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.5873. Min Act: -0.0000

Data Index: 1316075 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.2563. Min Act: -0.0000

Data Index: 1143968 (The Pile)

Max Activating Token Index: 297

Text #17

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.4384. Min Act: -0.0000

Data Index: 341495 (The Pile)

Max Activating Token Index: 323

Text #18

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.3209. Min Act: -0.0000

Data Index: 206699 (The Pile)

Max Activating Token Index: 252

Text #19

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.2266. Min Act: -0.0000

Data Index: 1742471 (The Pile)

Max Activating Token Index: 988