Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1095 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.6780. Min Act: -0.1700

Data Index: 1104506 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.6623. Min Act: -0.1700

Data Index: 1279896 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.6467. Min Act: -0.1700

Data Index: 336534 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.6154. Min Act: -0.1700

Data Index: 156448 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.6154. Min Act: -0.1700

Data Index: 79019 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5527. Min Act: -0.1700

Data Index: 1000416 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5371. Min Act: -0.1700

Data Index: 497480 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5527. Min Act: -0.1700

Data Index: 301312 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5371. Min Act: -0.1700

Data Index: 236295 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5527. Min Act: -0.1700

Data Index: 802992 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5371. Min Act: -0.1700

Data Index: 552104 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5214. Min Act: -0.1700

Data Index: 1537901 (Python Code)

Max Activating Token Index: 616

Text #12

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.5214. Min Act: -0.1700

Data Index: 862100 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.4744. Min Act: -0.1700

Data Index: 194284 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.4901. Min Act: -0.1700

Data Index: 1457833 (Python Code)

Max Activating Token Index: 976

Text #15

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.4901. Min Act: -0.1700

Data Index: 446936 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.4744. Min Act: -0.1700

Data Index: 951800 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.4587. Min Act: -0.1700

Data Index: 837765 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.4587. Min Act: -0.1700

Data Index: 71962 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 3.6780. Min Range: -3.6780

Max Act: 3.4587. Min Act: -0.1700

Data Index: 303289 (C4 (Web Text))

Max Activating Token Index: 248