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

Dataset: Open Web Text

Neuron 2330 in Layer 5

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: 5.2934. Min Range: -5.2934

Max Act: 5.2934. Min Act: -0.1700

Data Index: 1449083 (Open Web Text)

Max Activating Token Index: 637

Text #1

Max Range: 5.2934. Min Range: -5.2934

Max Act: 5.0606. Min Act: -0.1700

Data Index: 4240702 (Open Web Text)

Max Activating Token Index: 635

Text #2

Max Range: 5.2934. Min Range: -5.2934

Max Act: 5.0482. Min Act: -0.1700

Data Index: 8225075 (Open Web Text)

Max Activating Token Index: 947

Text #3

Max Range: 5.2934. Min Range: -5.2934

Max Act: 5.0017. Min Act: -0.1700

Data Index: 1449081 (Open Web Text)

Max Activating Token Index: 815

Text #4

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.9359. Min Act: -0.1700

Data Index: 6016139 (Open Web Text)

Max Activating Token Index: 926

Text #5

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.9588. Min Act: -0.1700

Data Index: 4096246 (Open Web Text)

Max Activating Token Index: 151

Text #6

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.9392. Min Act: -0.1700

Data Index: 7972410 (Open Web Text)

Max Activating Token Index: 323

Text #7

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.9436. Min Act: -0.1700

Data Index: 8035847 (Open Web Text)

Max Activating Token Index: 529

Text #8

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.8927. Min Act: -0.1700

Data Index: 8621759 (Open Web Text)

Max Activating Token Index: 952

Text #9

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.8887. Min Act: -0.1700

Data Index: 2111975 (Open Web Text)

Max Activating Token Index: 883

Text #10

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.8988. Min Act: -0.1700

Data Index: 5509209 (Open Web Text)

Max Activating Token Index: 296

Text #11

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.8913. Min Act: -0.1700

Data Index: 4451558 (Open Web Text)

Max Activating Token Index: 500

Text #12

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.8803. Min Act: -0.1700

Data Index: 1983051 (Open Web Text)

Max Activating Token Index: 288

Text #13

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.8386. Min Act: -0.1700

Data Index: 1208340 (Open Web Text)

Max Activating Token Index: 455

Text #14

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.8559. Min Act: -0.1700

Data Index: 7972411 (Open Web Text)

Max Activating Token Index: 471

Text #15

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.8161. Min Act: -0.1700

Data Index: 2143950 (Open Web Text)

Max Activating Token Index: 774

Text #16

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.8265. Min Act: -0.1700

Data Index: 3219734 (Open Web Text)

Max Activating Token Index: 768

Text #17

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.8041. Min Act: -0.1700

Data Index: 5858713 (Open Web Text)

Max Activating Token Index: 799

Text #18

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.8113. Min Act: -0.1700

Data Index: 4153546 (Open Web Text)

Max Activating Token Index: 928

Text #19

Max Range: 5.2934. Min Range: -5.2934

Max Act: 4.7954. Min Act: -0.1700

Data Index: 7473065 (Open Web Text)

Max Activating Token Index: 720