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

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

Neuron 3475 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0818. Min Range: -8.0818

Max Act: 8.0818. Min Act: -0.0000

Data Index: 1223593 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 8.0818. Min Range: -8.0818

Max Act: 7.9729. Min Act: -0.0000

Data Index: 598336 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 8.0818. Min Range: -8.0818

Max Act: 7.7436. Min Act: -0.0000

Data Index: 835156 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 8.0818. Min Range: -8.0818

Max Act: 7.5874. Min Act: -0.0000

Data Index: 869603 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 8.0818. Min Range: -8.0818

Max Act: 7.5598. Min Act: -0.0000

Data Index: 251427 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 8.0818. Min Range: -8.0818

Max Act: 7.7251. Min Act: -0.0000

Data Index: 1109518 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 8.0818. Min Range: -8.0818

Max Act: 7.3890. Min Act: -0.0000

Data Index: 977883 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 8.0818. Min Range: -8.0818

Max Act: 7.4745. Min Act: -0.0000

Data Index: 266557 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 8.0818. Min Range: -8.0818

Max Act: 7.2434. Min Act: -0.0000

Data Index: 419537 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 8.0818. Min Range: -8.0818

Max Act: 7.2088. Min Act: -0.0000

Data Index: 1266239 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 8.0818. Min Range: -8.0818

Max Act: 7.1943. Min Act: -0.0000

Data Index: 771613 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 8.0818. Min Range: -8.0818

Max Act: 7.1969. Min Act: -0.0000

Data Index: 793971 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 8.0818. Min Range: -8.0818

Max Act: 7.0906. Min Act: -0.0000

Data Index: 651240 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 8.0818. Min Range: -8.0818

Max Act: 7.2321. Min Act: -0.0000

Data Index: 490963 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 8.0818. Min Range: -8.0818

Max Act: 6.9533. Min Act: -0.0000

Data Index: 568658 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 8.0818. Min Range: -8.0818

Max Act: 6.8660. Min Act: -0.0000

Data Index: 1043995 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 8.0818. Min Range: -8.0818

Max Act: 6.8363. Min Act: -0.0000

Data Index: 884935 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 8.0818. Min Range: -8.0818

Max Act: 6.6802. Min Act: -0.0000

Data Index: 749592 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 8.0818. Min Range: -8.0818

Max Act: 6.8392. Min Act: -0.0000

Data Index: 438437 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 8.0818. Min Range: -8.0818

Max Act: 6.8498. Min Act: -0.0000

Data Index: 110958 (C4 (Web Text))

Max Activating Token Index: 51