Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4806 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1362. Min Act: -0.0001

Data Index: 31728 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1270. Min Act: -0.0001

Data Index: 981703 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1177. Min Act: -0.0001

Data Index: 1103625 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1182. Min Act: -0.0001

Data Index: 479549 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1203240 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1071. Min Act: -0.0001

Data Index: 473996 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0956. Min Act: -0.0001

Data Index: 573291 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1060. Min Act: -0.0001

Data Index: 911747 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0986. Min Act: -0.0001

Data Index: 803348 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0924. Min Act: -0.0001

Data Index: 346927 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0852. Min Act: -0.0001

Data Index: 613181 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0987. Min Act: -0.0001

Data Index: 29126 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0885. Min Act: -0.0001

Data Index: 628028 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0966. Min Act: -0.0001

Data Index: 959750 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0947. Min Act: -0.0001

Data Index: 342754 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1204557 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0860. Min Act: -0.0001

Data Index: 57465 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0907. Min Act: -0.0001

Data Index: 857600 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0958. Min Act: -0.0001

Data Index: 974776 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0872. Min Act: -0.0001

Data Index: 543075 (C4 (Web Text))

Max Activating Token Index: 391