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

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

Neuron 3243 in Layer 0

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: 0.4872. Min Range: -0.4872

Max Act: 0.4840. Min Act: -0.0001

Data Index: 598712 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4872. Min Act: -0.0001

Data Index: 1063084 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4519. Min Act: -0.0001

Data Index: 1031556 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4475. Min Act: -0.0001

Data Index: 115489 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4422. Min Act: -0.0001

Data Index: 996977 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4380. Min Act: -0.0001

Data Index: 1161186 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4279. Min Act: -0.0001

Data Index: 564508 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4181. Min Act: -0.0001

Data Index: 20992 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4133. Min Act: -0.0001

Data Index: 904126 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4053. Min Act: -0.0001

Data Index: 1036175 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4118. Min Act: -0.0001

Data Index: 1288806 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3942. Min Act: -0.0001

Data Index: 1042061 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4026. Min Act: -0.0001

Data Index: 1050324 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3978. Min Act: -0.0001

Data Index: 1294262 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3983. Min Act: -0.0001

Data Index: 26562 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4083. Min Act: -0.0001

Data Index: 200601 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3934. Min Act: -0.0001

Data Index: 236369 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3849. Min Act: -0.0001

Data Index: 640144 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3904. Min Act: -0.0001

Data Index: 857701 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3954. Min Act: -0.0001

Data Index: 1050042 (C4 (Web Text))

Max Activating Token Index: 513