Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2579 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7963. Min Act: -0.0000

Data Index: 1070769 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.6033. Min Act: -0.0000

Data Index: 454700 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7945. Min Act: -0.0000

Data Index: 719081 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.5269. Min Act: -0.0000

Data Index: 18046 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.5451. Min Act: -0.0000

Data Index: 447975 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.5602. Min Act: -0.0000

Data Index: 90107 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.6949. Min Act: -0.0000

Data Index: 708702 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.5402. Min Act: -0.0000

Data Index: 1236654 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.6415. Min Act: -0.0000

Data Index: 415944 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.5307. Min Act: -0.0000

Data Index: 289531 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.5342. Min Act: -0.0000

Data Index: 701996 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.4976. Min Act: -0.0000

Data Index: 657548 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.4052. Min Act: -0.0000

Data Index: 389642 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.4519. Min Act: -0.0000

Data Index: 1095627 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.5269. Min Act: -0.0000

Data Index: 17899 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.3455. Min Act: -0.0000

Data Index: 843187 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.3948. Min Act: -0.0000

Data Index: 69248 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.3921. Min Act: -0.0000

Data Index: 1063091 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.4797. Min Act: -0.0000

Data Index: 527095 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.4016. Min Act: -0.0000

Data Index: 550625 (C4 (Web Text))

Max Activating Token Index: 556