Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 832 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.6056. Min Act: -0.1700

Data Index: 1074724 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.5339. Min Act: -0.1700

Data Index: 351293 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.4733. Min Act: -0.1700

Data Index: 839257 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.4650. Min Act: -0.1700

Data Index: 141851 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.4404. Min Act: -0.1700

Data Index: 1022400 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.4031. Min Act: -0.1700

Data Index: 429867 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.4462. Min Act: -0.1700

Data Index: 809408 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.4273. Min Act: -0.1700

Data Index: 1040736 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.3814. Min Act: -0.1700

Data Index: 111224 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.3818. Min Act: -0.1700

Data Index: 1151563 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.3692. Min Act: -0.1700

Data Index: 325165 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.4038. Min Act: -0.1700

Data Index: 170861 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.3614. Min Act: -0.1700

Data Index: 891831 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.3727. Min Act: -0.1700

Data Index: 1188803 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.3163. Min Act: -0.1700

Data Index: 1194785 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.3574. Min Act: -0.1700

Data Index: 417692 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.3524. Min Act: -0.1700

Data Index: 479042 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.3520. Min Act: -0.1700

Data Index: 542061 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.3361. Min Act: -0.1700

Data Index: 821997 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 3.6056. Min Range: -3.6056

Max Act: 3.3062. Min Act: -0.1700

Data Index: 228979 (C4 (Web Text))

Max Activating Token Index: 275