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

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

Neuron 4057 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.1096. Min Act: -0.0001

Data Index: 112789 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.1037. Min Act: -0.0001

Data Index: 526909 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.1044. Min Act: -0.0001

Data Index: 949492 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0896. Min Act: -0.0001

Data Index: 678042 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0723. Min Act: -0.0001

Data Index: 1188565 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0869. Min Act: -0.0001

Data Index: 12589 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0637. Min Act: -0.0001

Data Index: 983598 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0733. Min Act: -0.0001

Data Index: 794721 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0340. Min Act: -0.0001

Data Index: 154383 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0294. Min Act: -0.0001

Data Index: 722007 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0283. Min Act: -0.0001

Data Index: 410517 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0196. Min Act: -0.0001

Data Index: 827997 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0244. Min Act: -0.0001

Data Index: 92634 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0153. Min Act: -0.0001

Data Index: 286265 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0253. Min Act: -0.0001

Data Index: 1228395 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0063. Min Act: -0.0001

Data Index: 1312200 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0366. Min Act: -0.0001

Data Index: 140290 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0143. Min Act: -0.0001

Data Index: 1297964 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0181. Min Act: -0.0001

Data Index: 475169 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0156. Min Act: -0.0001

Data Index: 569174 (C4 (Web Text))

Max Activating Token Index: 355