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

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

Neuron 2069 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: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0001

Data Index: 45593 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0001

Data Index: 458414 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0136. Min Act: -0.0001

Data Index: 841958 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0135. Min Act: -0.0001

Data Index: 574212 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0135. Min Act: -0.0001

Data Index: 439036 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0134. Min Act: -0.0001

Data Index: 1013059 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0136. Min Act: -0.0001

Data Index: 1262210 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0001

Data Index: 601632 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0135. Min Act: -0.0001

Data Index: 10026 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0132. Min Act: -0.0001

Data Index: 778061 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0001

Data Index: 894229 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0133. Min Act: -0.0001

Data Index: 43648 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0132. Min Act: -0.0002

Data Index: 229525 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0134. Min Act: -0.0001

Data Index: 326415 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0001

Data Index: 1080579 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0132. Min Act: -0.0001

Data Index: 974522 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0134. Min Act: -0.0001

Data Index: 1060255 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0130. Min Act: -0.0001

Data Index: 40755 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0134. Min Act: -0.0001

Data Index: 865611 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0132. Min Act: -0.0001

Data Index: 716718 (C4 (Web Text))

Max Activating Token Index: 248