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

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

Neuron 1110 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: 0.5082. Min Range: -0.5082

Max Act: 0.5082. Min Act: -0.0001

Data Index: 1361125 (Python Code)

Max Activating Token Index: 183

Text #1

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1570733 (Python Code)

Max Activating Token Index: 640

Text #2

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4678. Min Act: -0.0001

Data Index: 1500344 (Python Code)

Max Activating Token Index: 806

Text #3

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1563960 (Python Code)

Max Activating Token Index: 62

Text #4

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1511065 (Python Code)

Max Activating Token Index: 772

Text #5

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4436. Min Act: -0.0001

Data Index: 1523492 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4744. Min Act: -0.0000

Data Index: 1632724 (Python Code)

Max Activating Token Index: 782

Text #7

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1472106 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1575053 (Python Code)

Max Activating Token Index: 394

Text #9

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1429127 (Python Code)

Max Activating Token Index: 61

Text #10

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4444. Min Act: -0.0001

Data Index: 1561751 (Python Code)

Max Activating Token Index: 134

Text #11

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4295. Min Act: -0.0001

Data Index: 1572192 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1627868 (Python Code)

Max Activating Token Index: 455

Text #13

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1435955 (Python Code)

Max Activating Token Index: 58

Text #14

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4268. Min Act: -0.0001

Data Index: 1448533 (Python Code)

Max Activating Token Index: 598

Text #15

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4350. Min Act: -0.0001

Data Index: 1393058 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1571967 (Python Code)

Max Activating Token Index: 299

Text #17

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1555852 (Python Code)

Max Activating Token Index: 379

Text #18

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1501714 (Python Code)

Max Activating Token Index: 400

Text #19

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1442257 (Python Code)

Max Activating Token Index: 303