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

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

Neuron 2079 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.3756. Min Act: -0.0001

Data Index: 548355 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.3208. Min Act: -0.0001

Data Index: 753521 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2820. Min Act: -0.0001

Data Index: 1051194 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2696. Min Act: -0.0001

Data Index: 133986 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2514. Min Act: -0.0001

Data Index: 220285 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2469. Min Act: -0.0001

Data Index: 662091 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2441. Min Act: -0.0001

Data Index: 805454 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2772. Min Act: -0.0001

Data Index: 975420 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2273. Min Act: -0.0001

Data Index: 529885 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2484. Min Act: -0.0001

Data Index: 360109 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2417. Min Act: -0.0001

Data Index: 182102 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2524. Min Act: -0.0001

Data Index: 433305 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2375. Min Act: -0.0001

Data Index: 598382 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2393. Min Act: -0.0001

Data Index: 658717 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2093. Min Act: -0.0001

Data Index: 145540 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2390. Min Act: -0.0001

Data Index: 863085 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2384. Min Act: -0.0001

Data Index: 1329930 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2218. Min Act: -0.0001

Data Index: 574842 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2183. Min Act: -0.0001

Data Index: 777319 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.3756. Min Range: -0.3756

Max Act: 0.2268. Min Act: -0.0001

Data Index: 975814 (C4 (Web Text))

Max Activating Token Index: 580