Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5406 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.9259. Min Act: -0.0000

Data Index: 427955 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.5966. Min Act: -0.0000

Data Index: 1271841 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.7399. Min Act: -0.0000

Data Index: 1116598 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.7365. Min Act: -0.0000

Data Index: 270629 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.5818. Min Act: -0.0000

Data Index: 1061452 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.5658. Min Act: -0.0000

Data Index: 877259 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.3169. Min Act: -0.0000

Data Index: 550228 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.4440. Min Act: -0.0000

Data Index: 1353903 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.4859. Min Act: -0.0000

Data Index: 776711 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.5162. Min Act: -0.0000

Data Index: 660043 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.4775. Min Act: -0.0001

Data Index: 1138417 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.3618. Min Act: -0.0000

Data Index: 1149540 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.2271. Min Act: -0.0000

Data Index: 124155 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.2666. Min Act: -0.0000

Data Index: 1155002 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.6676. Min Act: -0.0000

Data Index: 342747 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 2.9259. Min Range: -2.9259

Max Act: 1.9718. Min Act: -0.0000

Data Index: 1278070 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.2708. Min Act: -0.0001

Data Index: 1271865 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.2550. Min Act: -0.0000

Data Index: 88123 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.1467. Min Act: -0.0000

Data Index: 136504 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 2.9259. Min Range: -2.9259

Max Act: 2.2281. Min Act: -0.0000

Data Index: 60101 (C4 (Web Text))

Max Activating Token Index: 998