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

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

Neuron 1639 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1254261 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.3366. Min Act: -0.0000

Data Index: 632717 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2468. Min Act: -0.0001

Data Index: 864554 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2546. Min Act: -0.0000

Data Index: 473952 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2517. Min Act: -0.0000

Data Index: 860750 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2753. Min Act: -0.0001

Data Index: 865942 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2584. Min Act: -0.0000

Data Index: 683796 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1286171 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1325136 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2615. Min Act: -0.0001

Data Index: 193571 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1250596 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2340. Min Act: -0.0001

Data Index: 829923 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2433. Min Act: -0.0001

Data Index: 671014 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2279. Min Act: -0.0000

Data Index: 836014 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2290. Min Act: -0.0001

Data Index: 308650 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1018724 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2259. Min Act: -0.0001

Data Index: 840512 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2565. Min Act: -0.0000

Data Index: 796867 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2298. Min Act: -0.0000

Data Index: 65507 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2193. Min Act: -0.0000

Data Index: 831343 (C4 (Web Text))

Max Activating Token Index: 707