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

Dataset: Open Web Text

Neuron 2983 in Layer 6

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: 4.4174. Min Range: -4.4174

Max Act: 4.4174. Min Act: -0.1700

Data Index: 7129230 (Open Web Text)

Max Activating Token Index: 288

Text #1

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.2976. Min Act: -0.1700

Data Index: 864425 (Open Web Text)

Max Activating Token Index: 506

Text #2

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.2777. Min Act: -0.1700

Data Index: 4661457 (Open Web Text)

Max Activating Token Index: 249

Text #3

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.2457. Min Act: -0.1700

Data Index: 8718441 (Open Web Text)

Max Activating Token Index: 148

Text #4

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.1571. Min Act: -0.1700

Data Index: 26561 (Open Web Text)

Max Activating Token Index: 587

Text #5

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.1657. Min Act: -0.1700

Data Index: 7021728 (Open Web Text)

Max Activating Token Index: 647

Text #6

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.0877. Min Act: -0.1700

Data Index: 1290748 (Open Web Text)

Max Activating Token Index: 720

Text #7

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.0477. Min Act: -0.1700

Data Index: 5187794 (Open Web Text)

Max Activating Token Index: 746

Text #8

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.0632. Min Act: -0.1700

Data Index: 3604131 (Open Web Text)

Max Activating Token Index: 943

Text #9

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.0576. Min Act: -0.1700

Data Index: 1538421 (Open Web Text)

Max Activating Token Index: 133

Text #10

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.0366. Min Act: -0.1700

Data Index: 7916613 (Open Web Text)

Max Activating Token Index: 215

Text #11

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.0180. Min Act: -0.1700

Data Index: 6060625 (Open Web Text)

Max Activating Token Index: 505

Text #12

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.0232. Min Act: -0.1700

Data Index: 8777933 (Open Web Text)

Max Activating Token Index: 417

Text #13

Max Range: 4.4174. Min Range: -4.4174

Max Act: 3.9808. Min Act: -0.1700

Data Index: 8682218 (Open Web Text)

Max Activating Token Index: 874

Text #14

Max Range: 4.4174. Min Range: -4.4174

Max Act: 3.9924. Min Act: -0.1700

Data Index: 4726187 (Open Web Text)

Max Activating Token Index: 430

Text #15

Max Range: 4.4174. Min Range: -4.4174

Max Act: 3.9720. Min Act: -0.1700

Data Index: 4669605 (Open Web Text)

Max Activating Token Index: 933

Text #16

Max Range: 4.4174. Min Range: -4.4174

Max Act: 4.0013. Min Act: -0.1700

Data Index: 3036005 (Open Web Text)

Max Activating Token Index: 899

Text #17

Max Range: 4.4174. Min Range: -4.4174

Max Act: 3.9956. Min Act: -0.1700

Data Index: 4691300 (Open Web Text)

Max Activating Token Index: 274

Text #18

Max Range: 4.4174. Min Range: -4.4174

Max Act: 3.9836. Min Act: -0.1700

Data Index: 299610 (Open Web Text)

Max Activating Token Index: 139

Text #19

Max Range: 4.4174. Min Range: -4.4174

Max Act: 3.9664. Min Act: -0.1700

Data Index: 2519541 (Open Web Text)

Max Activating Token Index: 464