Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 934 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.6792. Min Act: -0.1700

Data Index: 610657 (Open Web Text)

Max Activating Token Index: 180

Text #1

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.6327. Min Act: -0.1700

Data Index: 4984350 (Open Web Text)

Max Activating Token Index: 758

Text #2

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.6186. Min Act: -0.1700

Data Index: 5770790 (Open Web Text)

Max Activating Token Index: 538

Text #3

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.5615. Min Act: -0.1700

Data Index: 6390320 (Open Web Text)

Max Activating Token Index: 485

Text #4

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.5240. Min Act: -0.1700

Data Index: 7267697 (Open Web Text)

Max Activating Token Index: 637

Text #5

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4957. Min Act: -0.1700

Data Index: 4566736 (Open Web Text)

Max Activating Token Index: 890

Text #6

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4708. Min Act: -0.1700

Data Index: 173626 (Open Web Text)

Max Activating Token Index: 715

Text #7

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4688. Min Act: -0.1700

Data Index: 178685 (Open Web Text)

Max Activating Token Index: 129

Text #8

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4510. Min Act: -0.1700

Data Index: 5528358 (Open Web Text)

Max Activating Token Index: 52

Text #9

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4591. Min Act: -0.1700

Data Index: 6334512 (Open Web Text)

Max Activating Token Index: 363

Text #10

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4443. Min Act: -0.1700

Data Index: 1265823 (Open Web Text)

Max Activating Token Index: 771

Text #11

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.3997. Min Act: -0.1700

Data Index: 4463936 (Open Web Text)

Max Activating Token Index: 917

Text #12

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4152. Min Act: -0.1700

Data Index: 6780173 (Open Web Text)

Max Activating Token Index: 526

Text #13

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4518. Min Act: -0.1700

Data Index: 2055541 (Open Web Text)

Max Activating Token Index: 593

Text #14

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4460. Min Act: -0.1700

Data Index: 6788126 (Open Web Text)

Max Activating Token Index: 747

Text #15

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4466. Min Act: -0.1700

Data Index: 1208343 (Open Web Text)

Max Activating Token Index: 36

Text #16

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4135. Min Act: -0.1700

Data Index: 19160 (Open Web Text)

Max Activating Token Index: 875

Text #17

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4198. Min Act: -0.1700

Data Index: 7509032 (Open Web Text)

Max Activating Token Index: 453

Text #18

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4318. Min Act: -0.1700

Data Index: 4022041 (Open Web Text)

Max Activating Token Index: 473

Text #19

Max Range: 2.6792. Min Range: -2.6792

Max Act: 2.4291. Min Act: -0.1700

Data Index: 7724600 (Open Web Text)

Max Activating Token Index: 638