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

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

Neuron 1267 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: 4.3933. Min Range: -4.3933

Max Act: 4.3933. Min Act: -0.1700

Data Index: 1342099 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.3053. Min Act: -0.1700

Data Index: 655209 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.3292. Min Act: -0.1700

Data Index: 739950 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.2660. Min Act: -0.1700

Data Index: 64518 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.2395. Min Act: -0.1700

Data Index: 128076 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.2539. Min Act: -0.1700

Data Index: 534139 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.2762. Min Act: -0.1700

Data Index: 1130390 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.2200. Min Act: -0.1700

Data Index: 1231744 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.2279. Min Act: -0.1700

Data Index: 1555618 (Python Code)

Max Activating Token Index: 115

Text #9

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.2328. Min Act: -0.1700

Data Index: 1543550 (Python Code)

Max Activating Token Index: 251

Text #10

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.2183. Min Act: -0.1700

Data Index: 85583 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.2297. Min Act: -0.1700

Data Index: 10132 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.2012. Min Act: -0.1700

Data Index: 366211 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.1962. Min Act: -0.1700

Data Index: 498385 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.1712. Min Act: -0.1700

Data Index: 686799 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.1681. Min Act: -0.1700

Data Index: 360023 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.1901. Min Act: -0.1700

Data Index: 847989 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.1635. Min Act: -0.1700

Data Index: 928580 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.1936. Min Act: -0.1700

Data Index: 86045 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 4.3933. Min Range: -4.3933

Max Act: 4.1489. Min Act: -0.1700

Data Index: 1043812 (C4 (Web Text))

Max Activating Token Index: 775