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

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

Neuron 2592 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1107. Min Range: -3.1107

Max Act: 3.0444. Min Act: -0.0000

Data Index: 589616 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.9027. Min Act: -0.0000

Data Index: 54287 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 3.1107. Min Range: -3.1107

Max Act: 3.1107. Min Act: -0.0000

Data Index: 1071284 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.9400. Min Act: -0.0000

Data Index: 484994 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.9176. Min Act: -0.0000

Data Index: 978426 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.8276. Min Act: -0.0000

Data Index: 1357088 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.6884. Min Act: -0.0000

Data Index: 671518 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.8188. Min Act: -0.0000

Data Index: 1336798 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.7519. Min Act: -0.0000

Data Index: 1039097 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.6104. Min Act: -0.0000

Data Index: 360105 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.3879. Min Act: -0.0000

Data Index: 1254049 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.3364. Min Act: -0.0000

Data Index: 891126 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.4369. Min Act: -0.0000

Data Index: 590552 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.4319. Min Act: -0.0000

Data Index: 1142411 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.5532. Min Act: -0.0000

Data Index: 3100 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.4038. Min Act: -0.0000

Data Index: 729376 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.3842. Min Act: -0.0000

Data Index: 1164486 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.3866. Min Act: -0.0000

Data Index: 1124361 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.3670. Min Act: -0.0000

Data Index: 486732 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 3.1107. Min Range: -3.1107

Max Act: 2.3186. Min Act: -0.0000

Data Index: 1275356 (C4 (Web Text))

Max Activating Token Index: 405