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

Dataset: Open Web Text

Neuron 26 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: 5.4715. Min Range: -5.4715

Max Act: 5.4711. Min Act: -0.1700

Data Index: 3807684 (Open Web Text)

Max Activating Token Index: 741

Text #1

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.4715. Min Act: -0.1700

Data Index: 1663605 (Open Web Text)

Max Activating Token Index: 708

Text #2

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.4148. Min Act: -0.1700

Data Index: 6396255 (Open Web Text)

Max Activating Token Index: 117

Text #3

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3943. Min Act: -0.1700

Data Index: 2321215 (Open Web Text)

Max Activating Token Index: 752

Text #4

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3945. Min Act: -0.1700

Data Index: 8182168 (Open Web Text)

Max Activating Token Index: 36

Text #5

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3721. Min Act: -0.1700

Data Index: 7434795 (Open Web Text)

Max Activating Token Index: 944

Text #6

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3639. Min Act: -0.1700

Data Index: 5876155 (Open Web Text)

Max Activating Token Index: 708

Text #7

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3385. Min Act: -0.1700

Data Index: 891532 (Open Web Text)

Max Activating Token Index: 573

Text #8

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3639. Min Act: -0.1700

Data Index: 5620237 (Open Web Text)

Max Activating Token Index: 326

Text #9

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3396. Min Act: -0.1700

Data Index: 2289665 (Open Web Text)

Max Activating Token Index: 178

Text #10

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3654. Min Act: -0.1700

Data Index: 917965 (Open Web Text)

Max Activating Token Index: 336

Text #11

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3348. Min Act: -0.1700

Data Index: 6610937 (Open Web Text)

Max Activating Token Index: 769

Text #12

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3606. Min Act: -0.1700

Data Index: 4345784 (Open Web Text)

Max Activating Token Index: 828

Text #13

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3691. Min Act: -0.1700

Data Index: 4078504 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3052. Min Act: -0.1700

Data Index: 1753363 (Open Web Text)

Max Activating Token Index: 532

Text #15

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3021. Min Act: -0.1700

Data Index: 8079050 (Open Web Text)

Max Activating Token Index: 640

Text #16

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3171. Min Act: -0.1700

Data Index: 8683995 (Open Web Text)

Max Activating Token Index: 726

Text #17

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.3118. Min Act: -0.1700

Data Index: 6956835 (Open Web Text)

Max Activating Token Index: 910

Text #18

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.2805. Min Act: -0.1700

Data Index: 1118482 (Open Web Text)

Max Activating Token Index: 233

Text #19

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.2685. Min Act: -0.1700

Data Index: 1452500 (Open Web Text)

Max Activating Token Index: 286