Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2752 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1483. Min Act: -0.0000

Data Index: 510207 (The Pile)

Max Activating Token Index: 239

Text #1

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1169. Min Act: -0.0000

Data Index: 1658752 (The Pile)

Max Activating Token Index: 740

Text #2

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1529. Min Act: -0.0000

Data Index: 708979 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1277593 (The Pile)

Max Activating Token Index: 588

Text #4

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1258. Min Act: -0.0001

Data Index: 1234186 (The Pile)

Max Activating Token Index: 871

Text #5

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1382682 (The Pile)

Max Activating Token Index: 566

Text #6

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1302003 (The Pile)

Max Activating Token Index: 788

Text #7

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1303. Min Act: -0.0000

Data Index: 244815 (The Pile)

Max Activating Token Index: 521

Text #8

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1128. Min Act: -0.0000

Data Index: 219522 (The Pile)

Max Activating Token Index: 785

Text #9

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1114. Min Act: -0.0000

Data Index: 793177 (The Pile)

Max Activating Token Index: 240

Text #10

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1227. Min Act: -0.0000

Data Index: 744200 (The Pile)

Max Activating Token Index: 1013

Text #11

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1282825 (The Pile)

Max Activating Token Index: 759

Text #12

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1999240 (The Pile)

Max Activating Token Index: 325

Text #13

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1052. Min Act: -0.0000

Data Index: 110181 (The Pile)

Max Activating Token Index: 172

Text #14

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1215. Min Act: -0.0000

Data Index: 1952589 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1222. Min Act: -0.0001

Data Index: 433398 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1128. Min Act: -0.0000

Data Index: 729382 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1208. Min Act: -0.0000

Data Index: 822489 (The Pile)

Max Activating Token Index: 237

Text #18

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1521. Min Act: -0.0000

Data Index: 957024 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 0.1529. Min Range: -0.1529

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1163019 (The Pile)

Max Activating Token Index: 542