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

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

Neuron 1755 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0070. Min Range: -1.0070

Max Act: 1.0070. Min Act: -0.0000

Data Index: 651814 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.8794. Min Act: -0.0000

Data Index: 775974 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1365650 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1011570 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1632678 (Python Code)

Max Activating Token Index: 399

Text #5

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.5559. Min Act: -0.0000

Data Index: 501913 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.5385. Min Act: -0.0000

Data Index: 576785 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.5080. Min Act: -0.0000

Data Index: 535115 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.4789. Min Act: -0.0000

Data Index: 291638 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.4658. Min Act: -0.0000

Data Index: 572215 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.4448. Min Act: -0.0000

Data Index: 284758 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1325597 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1071241 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.4402. Min Act: -0.0000

Data Index: 541919 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.4176. Min Act: 0.0001

Data Index: 1259757 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.4168. Min Act: -0.0000

Data Index: 856219 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.4211. Min Act: 0.0001

Data Index: 906640 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.4219. Min Act: -0.0000

Data Index: 407358 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.4208. Min Act: -0.0000

Data Index: 824374 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.4204. Min Act: -0.0000

Data Index: 124745 (C4 (Web Text))

Max Activating Token Index: 149