Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 806 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1121279 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7152. Min Act: -0.0000

Data Index: 535595 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6620. Min Act: -0.0000

Data Index: 839179 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6977. Min Act: -0.0001

Data Index: 946190 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6444. Min Act: -0.0001

Data Index: 341924 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6256. Min Act: 0.0000

Data Index: 287670 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6698. Min Act: -0.0001

Data Index: 1293897 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6559. Min Act: -0.0001

Data Index: 229937 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6316. Min Act: -0.0001

Data Index: 47555 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1329457 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6825. Min Act: -0.0000

Data Index: 1242186 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5948. Min Act: -0.0000

Data Index: 473552 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5823. Min Act: -0.0001

Data Index: 30222 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1129745 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5997. Min Act: -0.0001

Data Index: 128571 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6182. Min Act: -0.0001

Data Index: 1030180 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6139. Min Act: -0.0001

Data Index: 537973 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5899. Min Act: -0.0001

Data Index: 788300 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6094. Min Act: -0.0001

Data Index: 1168971 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5941. Min Act: -0.0000

Data Index: 971609 (C4 (Web Text))

Max Activating Token Index: 316