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

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

Neuron 1004 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.7161. Min Act: -0.0001

Data Index: 283207 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.3660. Min Act: -0.0001

Data Index: 857417 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.3044. Min Act: -0.0001

Data Index: 1191267 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.1440. Min Act: -0.0001

Data Index: 64431 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0965. Min Act: -0.0001

Data Index: 1008718 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0815. Min Act: -0.0001

Data Index: 641218 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.1145. Min Act: -0.0001

Data Index: 295699 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0434. Min Act: -0.0001

Data Index: 1327698 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.1356. Min Act: -0.0001

Data Index: 939762 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0345. Min Act: -0.0001

Data Index: 524000 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0043. Min Act: -0.0001

Data Index: 1211966 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0267. Min Act: -0.0001

Data Index: 1157390 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 1.7161. Min Range: -1.7161

Max Act: 0.9881. Min Act: -0.0001

Data Index: 1343861 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0497. Min Act: -0.0001

Data Index: 392099 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0054. Min Act: -0.0001

Data Index: 464446 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0705. Min Act: -0.0001

Data Index: 778090 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0075. Min Act: -0.0001

Data Index: 1016079 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0399. Min Act: -0.0001

Data Index: 400118 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0370. Min Act: -0.0001

Data Index: 1021523 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 1.7161. Min Range: -1.7161

Max Act: 0.9603. Min Act: -0.0001

Data Index: 1302653 (C4 (Web Text))

Max Activating Token Index: 272