Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1518 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.1789. Min Range: -4.1789
Max Act: 4.1789. Min Act: -0.1700
Data Index: 480502 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1789. Min Range: -4.1789
Max Act: 4.1477. Min Act: -0.1700
Data Index: 1919384 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1789. Min Range: -4.1789
Max Act: 4.1477. Min Act: -0.1700
Data Index: 7837322 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1789. Min Range: -4.1789
Max Act: 4.0852. Min Act: -0.1700
Data Index: 2108129 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1789. Min Range: -4.1789
Max Act: 4.1477. Min Act: -0.1700
Data Index: 27290 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1789. Min Range: -4.1789
Max Act: 4.0852. Min Act: -0.1700
Data Index: 1819109 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1789. Min Range: -4.1789
Max Act: 4.0539. Min Act: -0.1700
Data Index: 6232314 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1789. Min Range: -4.1789
Max Act: 4.0539. Min Act: -0.1700
Data Index: 648110 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1789. Min Range: -4.1789
Max Act: 4.0227. Min Act: -0.1700
Data Index: 1365485 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1789. Min Range: -4.1789
Max Act: 4.0539. Min Act: -0.1700
Data Index: 569409 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1789. Min Range: -4.1789
Max Act: 3.9914. Min Act: -0.1700
Data Index: 4284544 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1789. Min Range: -4.1789
Max Act: 3.9601. Min Act: -0.1700
Data Index: 4243140 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1789. Min Range: -4.1789
Max Act: 3.9914. Min Act: -0.1700
Data Index: 3726987 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1789. Min Range: -4.1789
Max Act: 3.9914. Min Act: -0.1700
Data Index: 8106490 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1789. Min Range: -4.1789
Max Act: 3.9914. Min Act: -0.1700
Data Index: 7774046 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1789. Min Range: -4.1789
Max Act: 3.9914. Min Act: -0.1700
Data Index: 6998090 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1789. Min Range: -4.1789
Max Act: 3.9601. Min Act: -0.1700
Data Index: 2467725 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1789. Min Range: -4.1789
Max Act: 3.9601. Min Act: -0.1700
Data Index: 2418029 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1789. Min Range: -4.1789
Max Act: 3.9601. Min Act: -0.1700
Data Index: 4703131 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1789. Min Range: -4.1789
Max Act: 3.9289. Min Act: -0.1700
Data Index: 3806517 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19