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

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

Neuron 2380 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 3.0106. Min Range: -3.0106

Max Act: 3.0106. Min Act: -0.0002

Data Index: 109076 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.9247. Min Act: -0.0003

Data Index: 645081 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.7011. Min Act: -0.0002

Data Index: 1317340 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.6631. Min Act: -0.0002

Data Index: 834977 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.5712. Min Act: -0.0002

Data Index: 822293 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.4980. Min Act: -0.0002

Data Index: 1194569 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.5132. Min Act: -0.0002

Data Index: 384120 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.5418. Min Act: -0.0003

Data Index: 284880 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.5425. Min Act: -0.0002

Data Index: 993065 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.4350. Min Act: -0.0002

Data Index: 1332121 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.4454. Min Act: -0.0002

Data Index: 757807 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.4666. Min Act: -0.0002

Data Index: 125114 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.3478. Min Act: -0.0002

Data Index: 73903 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.3457. Min Act: -0.0003

Data Index: 144577 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.4680. Min Act: -0.0002

Data Index: 143138 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.4336. Min Act: -0.0002

Data Index: 215269 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.4200. Min Act: -0.0002

Data Index: 508643 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.3074. Min Act: -0.0003

Data Index: 1162065 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.2930. Min Act: -0.0002

Data Index: 127055 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 3.0106. Min Range: -3.0106

Max Act: 2.2857. Min Act: -0.0002

Data Index: 708381 (C4 (Web Text))

Max Activating Token Index: 519