Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3713 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 7.0876. Min Range: -7.0876

Max Act: 7.0876. Min Act: -0.0000

Data Index: 1266128 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 7.0876. Min Range: -7.0876

Max Act: 6.2155. Min Act: -0.0000

Data Index: 422111 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 7.0876. Min Range: -7.0876

Max Act: 6.2902. Min Act: -0.0000

Data Index: 427561 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 7.0876. Min Range: -7.0876

Max Act: 6.2288. Min Act: -0.0000

Data Index: 1165111 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 7.0876. Min Range: -7.0876

Max Act: 6.2177. Min Act: -0.0000

Data Index: 298272 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 7.0876. Min Range: -7.0876

Max Act: 5.9457. Min Act: -0.0000

Data Index: 154241 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 7.0876. Min Range: -7.0876

Max Act: 5.7732. Min Act: -0.0000

Data Index: 602022 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 7.0876. Min Range: -7.0876

Max Act: 5.6188. Min Act: -0.0000

Data Index: 807497 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 7.0876. Min Range: -7.0876

Max Act: 5.4593. Min Act: -0.0000

Data Index: 644424 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 7.0876. Min Range: -7.0876

Max Act: 5.2218. Min Act: -0.0000

Data Index: 695329 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 7.0876. Min Range: -7.0876

Max Act: 5.3854. Min Act: -0.0000

Data Index: 198002 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 7.0876. Min Range: -7.0876

Max Act: 5.1424. Min Act: -0.0000

Data Index: 327633 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 7.0876. Min Range: -7.0876

Max Act: 5.0875. Min Act: -0.0000

Data Index: 839809 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 7.0876. Min Range: -7.0876

Max Act: 4.8992. Min Act: -0.0000

Data Index: 994125 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 7.0876. Min Range: -7.0876

Max Act: 4.8548. Min Act: -0.0000

Data Index: 1099423 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 7.0876. Min Range: -7.0876

Max Act: 4.8098. Min Act: -0.0000

Data Index: 1184120 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 7.0876. Min Range: -7.0876

Max Act: 5.0038. Min Act: -0.0000

Data Index: 1282407 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 7.0876. Min Range: -7.0876

Max Act: 4.5638. Min Act: -0.0000

Data Index: 1128409 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 7.0876. Min Range: -7.0876

Max Act: 4.5161. Min Act: -0.0000

Data Index: 275474 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 7.0876. Min Range: -7.0876

Max Act: 4.4312. Min Act: -0.0000

Data Index: 1081811 (C4 (Web Text))

Max Activating Token Index: 652