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

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

Neuron 4343 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: 0.6140. Min Range: -0.6140

Max Act: 0.6082. Min Act: -0.0000

Data Index: 846803 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1523167 (Python Code)

Max Activating Token Index: 762

Text #2

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1572861 (Python Code)

Max Activating Token Index: 242

Text #3

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1516949 (Python Code)

Max Activating Token Index: 339

Text #4

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1408967 (Python Code)

Max Activating Token Index: 752

Text #5

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1596242 (Python Code)

Max Activating Token Index: 259

Text #6

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1387486 (Python Code)

Max Activating Token Index: 630

Text #7

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1499229 (Python Code)

Max Activating Token Index: 650

Text #8

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1533824 (Python Code)

Max Activating Token Index: 942

Text #9

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1543835 (Python Code)

Max Activating Token Index: 873

Text #10

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1513720 (Python Code)

Max Activating Token Index: 330

Text #11

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1645556 (Python Code)

Max Activating Token Index: 310

Text #12

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1515019 (Python Code)

Max Activating Token Index: 899

Text #13

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1566104 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4113. Min Act: -0.0000

Data Index: 722763 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4479. Min Act: -0.0000

Data Index: 1379165 (Python Code)

Max Activating Token Index: 412

Text #16

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1654036 (Python Code)

Max Activating Token Index: 765

Text #17

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1401911 (Python Code)

Max Activating Token Index: 1009

Text #18

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1408645 (Python Code)

Max Activating Token Index: 945

Text #19

Max Range: 0.6140. Min Range: -0.6140

Max Act: 0.4156. Min Act: -0.0000

Data Index: 374571 (C4 (Web Text))

Max Activating Token Index: 156