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

Dataset: Open Web Text

Neuron 2756 in Layer 1

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: 3.9030. Min Range: -3.9030

Max Act: 3.8988. Min Act: -0.1700

Data Index: 5861717 (Open Web Text)

Max Activating Token Index: 389

Text #1

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.8945. Min Act: -0.1700

Data Index: 4819745 (Open Web Text)

Max Activating Token Index: 98

Text #2

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.9030. Min Act: -0.1700

Data Index: 7858064 (Open Web Text)

Max Activating Token Index: 167

Text #3

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.8575. Min Act: -0.1700

Data Index: 2488710 (Open Web Text)

Max Activating Token Index: 920

Text #4

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.8619. Min Act: -0.1700

Data Index: 2969620 (Open Web Text)

Max Activating Token Index: 511

Text #5

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.8173. Min Act: -0.1700

Data Index: 8645733 (Open Web Text)

Max Activating Token Index: 347

Text #6

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.8239. Min Act: -0.1700

Data Index: 4535264 (Open Web Text)

Max Activating Token Index: 442

Text #7

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.8154. Min Act: -0.1700

Data Index: 8817850 (Open Web Text)

Max Activating Token Index: 112

Text #8

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.8392. Min Act: -0.1700

Data Index: 3263568 (Open Web Text)

Max Activating Token Index: 1019

Text #9

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.8120. Min Act: -0.1700

Data Index: 5241728 (Open Web Text)

Max Activating Token Index: 417

Text #10

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.8079. Min Act: -0.1700

Data Index: 6701406 (Open Web Text)

Max Activating Token Index: 356

Text #11

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.8286. Min Act: -0.1700

Data Index: 6380838 (Open Web Text)

Max Activating Token Index: 513

Text #12

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.7866. Min Act: -0.1700

Data Index: 4158350 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.7941. Min Act: -0.1700

Data Index: 6779860 (Open Web Text)

Max Activating Token Index: 314

Text #14

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.7935. Min Act: -0.1700

Data Index: 6625593 (Open Web Text)

Max Activating Token Index: 114

Text #15

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.7942. Min Act: -0.1700

Data Index: 149542 (Open Web Text)

Max Activating Token Index: 746

Text #16

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.8037. Min Act: -0.1700

Data Index: 1241525 (Open Web Text)

Max Activating Token Index: 96

Text #17

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.7977. Min Act: -0.1700

Data Index: 1195689 (Open Web Text)

Max Activating Token Index: 689

Text #18

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.8074. Min Act: -0.1700

Data Index: 3792418 (Open Web Text)

Max Activating Token Index: 124

Text #19

Max Range: 3.9030. Min Range: -3.9030

Max Act: 3.8021. Min Act: -0.1700

Data Index: 6034547 (Open Web Text)

Max Activating Token Index: 456