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

Dataset: Open Web Text

Neuron 1220 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: 3.9091. Min Range: -3.9091

Max Act: 3.9091. Min Act: -0.1700

Data Index: 2816868 (Open Web Text)

Max Activating Token Index: 236

Text #1

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.8236. Min Act: -0.1700

Data Index: 7067007 (Open Web Text)

Max Activating Token Index: 48

Text #2

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.7671. Min Act: -0.1700

Data Index: 114551 (Open Web Text)

Max Activating Token Index: 471

Text #3

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.7783. Min Act: -0.1700

Data Index: 6070094 (Open Web Text)

Max Activating Token Index: 693

Text #4

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.7557. Min Act: -0.1700

Data Index: 5047826 (Open Web Text)

Max Activating Token Index: 557

Text #5

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.7569. Min Act: -0.1700

Data Index: 5284331 (Open Web Text)

Max Activating Token Index: 69

Text #6

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.7248. Min Act: -0.1700

Data Index: 6742360 (Open Web Text)

Max Activating Token Index: 502

Text #7

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.7133. Min Act: -0.1700

Data Index: 1925945 (Open Web Text)

Max Activating Token Index: 629

Text #8

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.7156. Min Act: -0.1700

Data Index: 2650406 (Open Web Text)

Max Activating Token Index: 98

Text #9

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.7140. Min Act: -0.1700

Data Index: 875172 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.6840. Min Act: -0.1700

Data Index: 4534438 (Open Web Text)

Max Activating Token Index: 49

Text #11

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.6689. Min Act: -0.1700

Data Index: 2137165 (Open Web Text)

Max Activating Token Index: 295

Text #12

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.6770. Min Act: -0.1700

Data Index: 6895474 (Open Web Text)

Max Activating Token Index: 51

Text #13

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.6727. Min Act: -0.1700

Data Index: 4125210 (Open Web Text)

Max Activating Token Index: 885

Text #14

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.6607. Min Act: -0.1700

Data Index: 3621083 (Open Web Text)

Max Activating Token Index: 296

Text #15

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.6496. Min Act: -0.1700

Data Index: 7366594 (Open Web Text)

Max Activating Token Index: 534

Text #16

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.6764. Min Act: -0.1700

Data Index: 2859598 (Open Web Text)

Max Activating Token Index: 560

Text #17

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.6705. Min Act: -0.1700

Data Index: 2874028 (Open Web Text)

Max Activating Token Index: 198

Text #18

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.6783. Min Act: -0.1700

Data Index: 7832109 (Open Web Text)

Max Activating Token Index: 283

Text #19

Max Range: 3.9091. Min Range: -3.9091

Max Act: 3.6444. Min Act: -0.1700

Data Index: 3559256 (Open Web Text)

Max Activating Token Index: 35