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

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

Neuron 2203 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: 3.1934. Min Range: -3.1934

Max Act: 3.1934. Min Act: -0.0001

Data Index: 664404 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.1572. Min Act: -0.0001

Data Index: 401128 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.9731. Min Act: -0.0001

Data Index: 765317 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.9405. Min Act: -0.0001

Data Index: 744713 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.7714. Min Act: -0.0001

Data Index: 1341520 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.6360. Min Act: -0.0001

Data Index: 333953 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.5871. Min Act: -0.0001

Data Index: 219162 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.5386. Min Act: -0.0001

Data Index: 667612 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.6199. Min Act: -0.0001

Data Index: 807208 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.5122. Min Act: -0.0001

Data Index: 941350 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.4671. Min Act: -0.0001

Data Index: 998013 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.3451. Min Act: -0.0001

Data Index: 341964 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.2379. Min Act: -0.0001

Data Index: 1057904 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.4341. Min Act: -0.0001

Data Index: 492253 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.3233. Min Act: -0.0001

Data Index: 1042540 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.2719. Min Act: -0.0001

Data Index: 1199190 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.4650. Min Act: -0.0001

Data Index: 445149 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.3519. Min Act: -0.0001

Data Index: 99057 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.3229. Min Act: -0.0001

Data Index: 308271 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.5398. Min Act: -0.0001

Data Index: 244707 (C4 (Web Text))

Max Activating Token Index: 264