Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5076 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2934. Min Range: -2.2934

Max Act: 2.2934. Min Act: -0.0000

Data Index: 1558681 (Python Code)

Max Activating Token Index: 860

Text #1

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.9752. Min Act: -0.0000

Data Index: 1593952 (Python Code)

Max Activating Token Index: 344

Text #2

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.9089. Min Act: -0.0000

Data Index: 1225727 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.5853. Min Act: -0.0000

Data Index: 209532 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.5963. Min Act: -0.0000

Data Index: 772318 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.3776. Min Act: -0.0000

Data Index: 1575034 (Python Code)

Max Activating Token Index: 238

Text #6

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.4197. Min Act: -0.0000

Data Index: 1398882 (Python Code)

Max Activating Token Index: 359

Text #7

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.2787. Min Act: -0.0000

Data Index: 1464632 (Python Code)

Max Activating Token Index: 511

Text #8

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.2744. Min Act: -0.0000

Data Index: 1372363 (Python Code)

Max Activating Token Index: 544

Text #9

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1333115 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.3309. Min Act: -0.0000

Data Index: 647919 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.1526. Min Act: -0.0000

Data Index: 669438 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.2221. Min Act: -0.0000

Data Index: 165564 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.2899. Min Act: -0.0000

Data Index: 1594115 (Python Code)

Max Activating Token Index: 277

Text #14

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.1129. Min Act: -0.0000

Data Index: 1364609 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.1285. Min Act: -0.0000

Data Index: 1286082 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.1799. Min Act: -0.0000

Data Index: 933265 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.2714. Min Act: -0.0000

Data Index: 1377323 (Python Code)

Max Activating Token Index: 659

Text #18

Max Range: 2.2934. Min Range: -2.2934

Max Act: 1.2038. Min Act: -0.0000

Data Index: 1646157 (Python Code)

Max Activating Token Index: 833

Text #19

Max Range: 2.2934. Min Range: -2.2934

Max Act: 0.9901. Min Act: -0.0000

Data Index: 409404 (C4 (Web Text))

Max Activating Token Index: 892