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

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

Neuron 2717 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: 0.3007. Min Range: -0.3007

Max Act: 0.2846. Min Act: -0.0001

Data Index: 961661 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.3007. Min Act: -0.0001

Data Index: 176148 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2996. Min Act: -0.0001

Data Index: 1206578 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2646. Min Act: -0.0001

Data Index: 271967 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2712. Min Act: -0.0001

Data Index: 742699 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2433. Min Act: -0.0001

Data Index: 1173371 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2451. Min Act: -0.0001

Data Index: 984802 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2405. Min Act: -0.0001

Data Index: 294616 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2312. Min Act: -0.0001

Data Index: 1095149 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2510. Min Act: -0.0001

Data Index: 1053865 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2499. Min Act: -0.0001

Data Index: 24807 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2216. Min Act: -0.0001

Data Index: 1457291 (Python Code)

Max Activating Token Index: 22

Text #12

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2329. Min Act: -0.0001

Data Index: 924438 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2519. Min Act: -0.0001

Data Index: 298419 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2428. Min Act: -0.0001

Data Index: 1102837 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2419. Min Act: -0.0001

Data Index: 38853 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2358. Min Act: -0.0001

Data Index: 257152 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2489. Min Act: -0.0001

Data Index: 497741 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1011897 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2239. Min Act: -0.0001

Data Index: 1119001 (C4 (Web Text))

Max Activating Token Index: 971