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

Dataset: Open Web Text

Neuron 1758 in Layer 2

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: 3.3477. Min Range: -3.3477

Max Act: 3.3477. Min Act: -0.1700

Data Index: 3079668 (Open Web Text)

Max Activating Token Index: 673

Text #1

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.3342. Min Act: -0.1700

Data Index: 2986478 (Open Web Text)

Max Activating Token Index: 471

Text #2

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.3206. Min Act: -0.1700

Data Index: 6832508 (Open Web Text)

Max Activating Token Index: 279

Text #3

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.3062. Min Act: -0.1700

Data Index: 7680760 (Open Web Text)

Max Activating Token Index: 498

Text #4

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2939. Min Act: -0.1700

Data Index: 6832502 (Open Web Text)

Max Activating Token Index: 158

Text #5

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2758. Min Act: -0.1700

Data Index: 3593007 (Open Web Text)

Max Activating Token Index: 623

Text #6

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2886. Min Act: -0.1700

Data Index: 742808 (Open Web Text)

Max Activating Token Index: 139

Text #7

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2557. Min Act: -0.1700

Data Index: 1575687 (Open Web Text)

Max Activating Token Index: 204

Text #8

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2545. Min Act: -0.1700

Data Index: 7220063 (Open Web Text)

Max Activating Token Index: 103

Text #9

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2567. Min Act: -0.1700

Data Index: 8664628 (Open Web Text)

Max Activating Token Index: 287

Text #10

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2627. Min Act: -0.1700

Data Index: 6832499 (Open Web Text)

Max Activating Token Index: 148

Text #11

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2468. Min Act: -0.1700

Data Index: 6863155 (Open Web Text)

Max Activating Token Index: 32

Text #12

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2483. Min Act: -0.1700

Data Index: 3373332 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2354. Min Act: -0.1700

Data Index: 5861840 (Open Web Text)

Max Activating Token Index: 447

Text #14

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2308. Min Act: -0.1700

Data Index: 2460966 (Open Web Text)

Max Activating Token Index: 799

Text #15

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2553. Min Act: -0.1700

Data Index: 6821901 (Open Web Text)

Max Activating Token Index: 251

Text #16

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2316. Min Act: -0.1700

Data Index: 2511705 (Open Web Text)

Max Activating Token Index: 287

Text #17

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2129. Min Act: -0.1700

Data Index: 4902881 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2054. Min Act: -0.1700

Data Index: 4885422 (Open Web Text)

Max Activating Token Index: 753

Text #19

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2180. Min Act: -0.1700

Data Index: 2935578 (Open Web Text)

Max Activating Token Index: 933