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

Dataset: The Pile

Neuron 1085 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.4492. Min Act: -0.0000

Data Index: 1923859 (The Pile)

Max Activating Token Index: 663

Text #1

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.5175. Min Act: -0.0000

Data Index: 1155257 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1317117 (The Pile)

Max Activating Token Index: 802

Text #3

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.0591. Min Act: -0.0000

Data Index: 1288886 (The Pile)

Max Activating Token Index: 666

Text #4

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.0272. Min Act: -0.0000

Data Index: 988866 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.0738. Min Act: -0.0000

Data Index: 1341576 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.9836. Min Act: -0.0000

Data Index: 1355240 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 1.5175. Min Range: -1.5175

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1493033 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.8749. Min Act: -0.0000

Data Index: 307513 (The Pile)

Max Activating Token Index: 823

Text #9

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.8335. Min Act: -0.0000

Data Index: 277637 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1504234 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.9017. Min Act: -0.0000

Data Index: 966582 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1765643 (The Pile)

Max Activating Token Index: 32

Text #13

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.8475. Min Act: -0.0000

Data Index: 679757 (The Pile)

Max Activating Token Index: 495

Text #14

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1450685 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.8930. Min Act: -0.0000

Data Index: 400704 (The Pile)

Max Activating Token Index: 854

Text #16

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1339442 (The Pile)

Max Activating Token Index: 962

Text #17

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.8093. Min Act: -0.0000

Data Index: 961221 (The Pile)

Max Activating Token Index: 123

Text #18

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.8308. Min Act: -0.0000

Data Index: 511532 (The Pile)

Max Activating Token Index: 19

Text #19

Max Range: 1.5175. Min Range: -1.5175

Max Act: 0.7586. Min Act: -0.0000

Data Index: 238119 (The Pile)

Max Activating Token Index: 21