Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1651 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.8462. Min Act: -0.1700
Data Index: 2812446 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.6898. Min Act: -0.1700
Data Index: 7967012 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.6898. Min Act: -0.1700
Data Index: 3023299 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.6898. Min Act: -0.1700
Data Index: 4818431 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.6741. Min Act: -0.1700
Data Index: 623495 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.6585. Min Act: -0.1700
Data Index: 1354097 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.6585. Min Act: -0.1700
Data Index: 300803 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.6272. Min Act: -0.1700
Data Index: 8511658 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.6115. Min Act: -0.1700
Data Index: 1984379 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.5959. Min Act: -0.1700
Data Index: 5436429 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.6115. Min Act: -0.1700
Data Index: 1453332 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.5959. Min Act: -0.1700
Data Index: 6173119 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.5959. Min Act: -0.1700
Data Index: 4975684 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.5802. Min Act: -0.1700
Data Index: 2007460 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.5959. Min Act: -0.1700
Data Index: 5207515 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.5646. Min Act: -0.1700
Data Index: 4776377 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.5646. Min Act: -0.1700
Data Index: 3912086 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.5176. Min Act: -0.1700
Data Index: 3006977 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.5646. Min Act: -0.1700
Data Index: 5843680 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8462. Min Range: -3.8462
Max Act: 3.5489. Min Act: -0.1700
Data Index: 2007461 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19