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

Dataset: The Pile

Neuron 2620 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1466. Min Act: -0.0000

Data Index: 684320 (The Pile)

Max Activating Token Index: 779

Text #1

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.3235. Min Act: -0.0000

Data Index: 1021800 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2133. Min Act: -0.0000

Data Index: 1374076 (The Pile)

Max Activating Token Index: 865

Text #3

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2647. Min Act: -0.0000

Data Index: 801940 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.3090. Min Act: -0.0000

Data Index: 1006325 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2678. Min Act: -0.0000

Data Index: 1372727 (The Pile)

Max Activating Token Index: 591

Text #6

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1928955 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1477514 (The Pile)

Max Activating Token Index: 654

Text #8

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2989. Min Act: -0.0000

Data Index: 781375 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1960. Min Act: -0.0000

Data Index: 145205 (The Pile)

Max Activating Token Index: 650

Text #10

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1213. Min Act: -0.0000

Data Index: 1269800 (The Pile)

Max Activating Token Index: 529

Text #11

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1290. Min Act: -0.0000

Data Index: 638143 (The Pile)

Max Activating Token Index: 934

Text #12

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.0876. Min Act: -0.0000

Data Index: 281754 (The Pile)

Max Activating Token Index: 812

Text #13

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.3289. Min Act: -0.0000

Data Index: 1967742 (The Pile)

Max Activating Token Index: 472

Text #14

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.0993. Min Act: -0.0000

Data Index: 800897 (The Pile)

Max Activating Token Index: 440

Text #15

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1548. Min Act: -0.0000

Data Index: 150489 (The Pile)

Max Activating Token Index: 624

Text #16

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1288. Min Act: -0.0000

Data Index: 294687 (The Pile)

Max Activating Token Index: 567

Text #17

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1336. Min Act: -0.0000

Data Index: 444101 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1414. Min Act: -0.0000

Data Index: 229251 (The Pile)

Max Activating Token Index: 920

Text #19

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.0276. Min Act: -0.0000

Data Index: 621061 (The Pile)

Max Activating Token Index: 577