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

Dataset: Open Web Text

Neuron 1592 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: 3.0190. Min Range: -3.0190

Max Act: 3.0103. Min Act: -0.1700

Data Index: 8019900 (Open Web Text)

Max Activating Token Index: 507

Text #1

Max Range: 3.0190. Min Range: -3.0190

Max Act: 3.0190. Min Act: -0.1700

Data Index: 3267865 (Open Web Text)

Max Activating Token Index: 460

Text #2

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9879. Min Act: -0.1700

Data Index: 832754 (Open Web Text)

Max Activating Token Index: 491

Text #3

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9835. Min Act: -0.1700

Data Index: 7979977 (Open Web Text)

Max Activating Token Index: 733

Text #4

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9628. Min Act: -0.1700

Data Index: 3429658 (Open Web Text)

Max Activating Token Index: 560

Text #5

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9585. Min Act: -0.1700

Data Index: 8705056 (Open Web Text)

Max Activating Token Index: 810

Text #6

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9577. Min Act: -0.1700

Data Index: 6962773 (Open Web Text)

Max Activating Token Index: 341

Text #7

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9453. Min Act: -0.1700

Data Index: 4188066 (Open Web Text)

Max Activating Token Index: 883

Text #8

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9336. Min Act: -0.1700

Data Index: 1913270 (Open Web Text)

Max Activating Token Index: 54

Text #9

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9495. Min Act: -0.1700

Data Index: 6004970 (Open Web Text)

Max Activating Token Index: 440

Text #10

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9242. Min Act: -0.1700

Data Index: 523862 (Open Web Text)

Max Activating Token Index: 523

Text #11

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9307. Min Act: -0.1700

Data Index: 7588029 (Open Web Text)

Max Activating Token Index: 668

Text #12

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9133. Min Act: -0.1700

Data Index: 6256773 (Open Web Text)

Max Activating Token Index: 687

Text #13

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9188. Min Act: -0.1700

Data Index: 2981196 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9218. Min Act: -0.1700

Data Index: 6185613 (Open Web Text)

Max Activating Token Index: 113

Text #15

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9128. Min Act: -0.1700

Data Index: 7061249 (Open Web Text)

Max Activating Token Index: 525

Text #16

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9057. Min Act: -0.1700

Data Index: 1144650 (Open Web Text)

Max Activating Token Index: 443

Text #17

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9096. Min Act: -0.1700

Data Index: 1870242 (Open Web Text)

Max Activating Token Index: 808

Text #18

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.8847. Min Act: -0.1700

Data Index: 2402714 (Open Web Text)

Max Activating Token Index: 783

Text #19

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.8935. Min Act: -0.1700

Data Index: 2493007 (Open Web Text)

Max Activating Token Index: 536