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

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

Neuron 1536 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1061799 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.6794. Min Act: -0.0000

Data Index: 836595 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1182149 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1194527 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.5339. Min Act: -0.0000

Data Index: 452475 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.5385. Min Act: -0.0000

Data Index: 850096 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.4753. Min Act: -0.0000

Data Index: 83824 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.4817. Min Act: -0.0000

Data Index: 61509 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1005844 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1271053 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.3866. Min Act: -0.0001

Data Index: 1086358 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.3591. Min Act: -0.0000

Data Index: 176452 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.3767. Min Act: -0.0000

Data Index: 164364 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.3431. Min Act: -0.0000

Data Index: 232294 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1077099 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.3610. Min Act: -0.0000

Data Index: 541574 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1102218 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1336402 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1266802 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.9203. Min Range: -0.9203

Max Act: 0.3225. Min Act: -0.0001

Data Index: 1194940 (C4 (Web Text))

Max Activating Token Index: 502