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

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

Neuron 1902 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3216. Min Range: -5.3216

Max Act: 5.2329. Min Act: -0.0001

Data Index: 1222270 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 5.3216. Min Range: -5.3216

Max Act: 5.3216. Min Act: -0.0001

Data Index: 946791 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 5.3216. Min Range: -5.3216

Max Act: 5.1958. Min Act: -0.0001

Data Index: 1059303 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.7993. Min Act: -0.0001

Data Index: 1354221 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.4249. Min Act: -0.0001

Data Index: 1340930 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.7920. Min Act: -0.0001

Data Index: 180989 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.4303. Min Act: -0.0001

Data Index: 925314 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.4187. Min Act: -0.0001

Data Index: 1310259 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.2244. Min Act: -0.0001

Data Index: 828394 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.2201. Min Act: -0.0001

Data Index: 132751 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 5.3216. Min Range: -5.3216

Max Act: 5.2337. Min Act: -0.0001

Data Index: 18793 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.3084. Min Act: -0.0001

Data Index: 832189 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.3219. Min Act: -0.0001

Data Index: 400022 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.0463. Min Act: -0.0001

Data Index: 622591 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.0488. Min Act: -0.0001

Data Index: 440876 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.2140. Min Act: -0.0001

Data Index: 238040 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.1962. Min Act: -0.0001

Data Index: 42804 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 5.3216. Min Range: -5.3216

Max Act: 3.9997. Min Act: -0.0001

Data Index: 1251534 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.1485. Min Act: -0.0001

Data Index: 302608 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 5.3216. Min Range: -5.3216

Max Act: 4.1499. Min Act: -0.0001

Data Index: 446965 (C4 (Web Text))

Max Activating Token Index: 387