Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2387 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.1939. Min Act: -0.0003

Data Index: 77229 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0161. Min Act: -0.0003

Data Index: 192390 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0125. Min Act: -0.0003

Data Index: 61981 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0336. Min Act: -0.0003

Data Index: 453915 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0654. Min Act: -0.0003

Data Index: 348055 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0541. Min Act: -0.0003

Data Index: 1099196 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0096. Min Act: -0.0003

Data Index: 891256 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0301. Min Act: -0.0003

Data Index: 1305958 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9679. Min Act: -0.0003

Data Index: 263005 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0896. Min Act: -0.0003

Data Index: 459189 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9240. Min Act: -0.0003

Data Index: 1199990 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9779. Min Act: -0.0003

Data Index: 953924 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0364. Min Act: -0.0003

Data Index: 233478 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9950. Min Act: -0.0003

Data Index: 211824 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9629. Min Act: -0.0003

Data Index: 329376 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0182. Min Act: -0.0003

Data Index: 118365 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9144. Min Act: -0.0003

Data Index: 662079 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9753. Min Act: -0.0003

Data Index: 655116 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 1.1939. Min Range: -1.1939

Max Act: 0.9169. Min Act: -0.0003

Data Index: 1010685 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 1.1939. Min Range: -1.1939

Max Act: 1.0640. Min Act: -0.0003

Data Index: 1083163 (C4 (Web Text))

Max Activating Token Index: 184