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

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

Neuron 2555 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.5450. Min Act: -0.0000

Data Index: 995625 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.5167. Min Act: -0.0000

Data Index: 162030 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4987. Min Act: -0.0000

Data Index: 214851 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1308301 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1006909 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1131055 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1236251 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4495. Min Act: -0.0000

Data Index: 123622 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4361. Min Act: -0.0000

Data Index: 214450 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4033. Min Act: -0.0001

Data Index: 714804 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4142. Min Act: -0.0000

Data Index: 649785 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4273. Min Act: -0.0000

Data Index: 570054 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4027. Min Act: -0.0000

Data Index: 413969 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1131324 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3978. Min Act: -0.0000

Data Index: 946057 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4233. Min Act: -0.0000

Data Index: 1342453 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4082. Min Act: -0.0000

Data Index: 664347 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1125304 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4157. Min Act: -0.0000

Data Index: 311002 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4176. Min Act: -0.0001

Data Index: 351207 (C4 (Web Text))

Max Activating Token Index: 984