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

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

Neuron 2782 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3246. Min Act: -0.0001

Data Index: 813077 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3251. Min Act: -0.0001

Data Index: 1620048 (Python Code)

Max Activating Token Index: 374

Text #2

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2980. Min Act: -0.0001

Data Index: 1387081 (Python Code)

Max Activating Token Index: 197

Text #3

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2803. Min Act: -0.0001

Data Index: 1544178 (Python Code)

Max Activating Token Index: 891

Text #4

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3130. Min Act: -0.0001

Data Index: 1451184 (Python Code)

Max Activating Token Index: 282

Text #5

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2985. Min Act: -0.0001

Data Index: 1621597 (Python Code)

Max Activating Token Index: 981

Text #6

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3094. Min Act: -0.0001

Data Index: 1560199 (Python Code)

Max Activating Token Index: 776

Text #7

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2903. Min Act: -0.0001

Data Index: 1404115 (Python Code)

Max Activating Token Index: 802

Text #8

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2892. Min Act: -0.0001

Data Index: 1567650 (Python Code)

Max Activating Token Index: 1022

Text #9

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3214. Min Act: -0.0001

Data Index: 1445971 (Python Code)

Max Activating Token Index: 879

Text #10

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2869. Min Act: -0.0001

Data Index: 1536439 (Python Code)

Max Activating Token Index: 953

Text #11

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2990. Min Act: -0.0001

Data Index: 1444141 (Python Code)

Max Activating Token Index: 359

Text #12

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2545. Min Act: -0.0001

Data Index: 1501985 (Python Code)

Max Activating Token Index: 162

Text #13

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2832. Min Act: -0.0001

Data Index: 1473695 (Python Code)

Max Activating Token Index: 453

Text #14

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2939. Min Act: -0.0001

Data Index: 1362876 (Python Code)

Max Activating Token Index: 406

Text #15

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2722. Min Act: -0.0001

Data Index: 1649133 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2866. Min Act: -0.0001

Data Index: 1593216 (Python Code)

Max Activating Token Index: 641

Text #17

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1362283 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2728. Min Act: -0.0001

Data Index: 1435531 (Python Code)

Max Activating Token Index: 959

Text #19

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2753. Min Act: -0.0001

Data Index: 1575717 (Python Code)

Max Activating Token Index: 639