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

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

Neuron 13 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.9336. Min Act: -0.1700

Data Index: 541890 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.8085. Min Act: -0.1700

Data Index: 987367 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.8085. Min Act: -0.1700

Data Index: 1089170 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.8085. Min Act: -0.1700

Data Index: 462489 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.7616. Min Act: -0.1700

Data Index: 472069 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.7616. Min Act: -0.1700

Data Index: 334568 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.7303. Min Act: -0.1700

Data Index: 828677 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.7147. Min Act: -0.1700

Data Index: 292237 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.7303. Min Act: -0.1700

Data Index: 834068 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.7460. Min Act: -0.1700

Data Index: 477529 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.7303. Min Act: -0.1700

Data Index: 946005 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.6990. Min Act: -0.1700

Data Index: 328939 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.6990. Min Act: -0.1700

Data Index: 320259 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.6990. Min Act: -0.1700

Data Index: 89601 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.6521. Min Act: -0.1700

Data Index: 1316835 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.6834. Min Act: -0.1700

Data Index: 797981 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.6677. Min Act: -0.1700

Data Index: 950797 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.6521. Min Act: -0.1700

Data Index: 79944 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.6990. Min Act: -0.1700

Data Index: 810287 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 3.9336. Min Range: -3.9336

Max Act: 3.6677. Min Act: -0.1700

Data Index: 943502 (C4 (Web Text))

Max Activating Token Index: 666