Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 263 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 563253 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1321981 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0045. Min Act: -0.0003

Data Index: 33447 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0044. Min Act: -0.0003

Data Index: 1316324 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0043. Min Act: -0.0003

Data Index: 217719 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0042. Min Act: -0.0003

Data Index: 462020 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1416334 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0038. Min Act: -0.0003

Data Index: 1251268 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0039. Min Act: -0.0003

Data Index: 1015193 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0039. Min Act: -0.0003

Data Index: 1174497 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0038. Min Act: -0.0003

Data Index: 1046081 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0037. Min Act: -0.0003

Data Index: 79680 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0037. Min Act: -0.0003

Data Index: 900882 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0037. Min Act: -0.0003

Data Index: 166647 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0038. Min Act: -0.0003

Data Index: 521690 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0035. Min Act: -0.0003

Data Index: 787179 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1431422 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0037. Min Act: -0.0003

Data Index: 536482 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1030607 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0036. Min Act: -0.0003

Data Index: 604772 (C4 (Web Text))

Max Activating Token Index: 442