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

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

Neuron 6137 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.5428. Min Act: 0.0000

Data Index: 50815 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.5965. Min Act: -0.0000

Data Index: 386600 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.5816. Min Act: -0.0000

Data Index: 675672 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.5192. Min Act: -0.0000

Data Index: 543836 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.5137. Min Act: -0.0000

Data Index: 1110316 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.4844. Min Act: -0.0000

Data Index: 933349 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.4760. Min Act: -0.0000

Data Index: 864712 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.4513. Min Act: -0.0000

Data Index: 942103 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.4426. Min Act: -0.0000

Data Index: 860960 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.4434. Min Act: -0.0000

Data Index: 710279 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.3592. Min Act: -0.0000

Data Index: 585990 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.3364. Min Act: -0.0000

Data Index: 918291 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.3437. Min Act: -0.0000

Data Index: 641033 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.4130. Min Act: -0.0000

Data Index: 179319 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.3821. Min Act: -0.0000

Data Index: 92026 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.3838. Min Act: 0.0000

Data Index: 807274 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.3922. Min Act: -0.0000

Data Index: 335045 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.3064. Min Act: -0.0000

Data Index: 903443 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.3786. Min Act: -0.0000

Data Index: 729208 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 1.5965. Min Range: -1.5965

Max Act: 1.3706. Min Act: -0.0000

Data Index: 1130127 (C4 (Web Text))

Max Activating Token Index: 697