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

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

Neuron 3071 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1510. Min Act: -0.0002

Data Index: 474941 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1512. Min Act: -0.0002

Data Index: 1085804 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1384. Min Act: -0.0001

Data Index: 673146 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1318. Min Act: -0.0002

Data Index: 124571 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1318738 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1276816 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1324. Min Act: -0.0001

Data Index: 662790 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1218. Min Act: -0.0002

Data Index: 390366 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1212720 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1237. Min Act: -0.0002

Data Index: 641881 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1133472 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1137. Min Act: -0.0001

Data Index: 194742 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1130. Min Act: -0.0001

Data Index: 237543 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1087. Min Act: -0.0002

Data Index: 107720 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1019670 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1032. Min Act: -0.0001

Data Index: 584958 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1051. Min Act: -0.0001

Data Index: 411982 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1052. Min Act: -0.0002

Data Index: 113871 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1031. Min Act: -0.0002

Data Index: 207442 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1128. Min Act: -0.0002

Data Index: 1267398 (C4 (Web Text))

Max Activating Token Index: 907