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

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

Neuron 2004 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.9822. Min Act: -0.0000

Data Index: 677574 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 3.1291. Min Range: -3.1291

Max Act: 3.1291. Min Act: -0.0000

Data Index: 738248 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.6585. Min Act: -0.0000

Data Index: 1235429 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.4980. Min Act: -0.0000

Data Index: 1104067 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.7090. Min Act: -0.0000

Data Index: 589788 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.7051. Min Act: -0.0000

Data Index: 1331066 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.5043. Min Act: -0.0000

Data Index: 680737 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.3783. Min Act: -0.0000

Data Index: 47082 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.3463. Min Act: -0.0000

Data Index: 740436 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.3157. Min Act: -0.0000

Data Index: 115730 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.1595. Min Act: -0.0000

Data Index: 1001447 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.1383. Min Act: -0.0000

Data Index: 838739 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.1355. Min Act: -0.0000

Data Index: 80220 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.2545. Min Act: -0.0000

Data Index: 1063207 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.2303. Min Act: -0.0000

Data Index: 369053 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.2865. Min Act: -0.0000

Data Index: 514874 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 3.1291. Min Range: -3.1291

Max Act: 1.9707. Min Act: -0.0000

Data Index: 1158176 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.0599. Min Act: -0.0000

Data Index: 60889 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 3.1291. Min Range: -3.1291

Max Act: 2.0521. Min Act: -0.0000

Data Index: 568985 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 3.1291. Min Range: -3.1291

Max Act: 1.8272. Min Act: -0.0000

Data Index: 1047494 (C4 (Web Text))

Max Activating Token Index: 313