Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4173 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.5116. Min Act: -0.1700
Data Index: 1672540 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.4803. Min Act: -0.1700
Data Index: 4847026 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.3866. Min Act: -0.1700
Data Index: 5803964 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.3241. Min Act: -0.1700
Data Index: 8756054 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.2616. Min Act: -0.1700
Data Index: 6988539 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.2303. Min Act: -0.1700
Data Index: 4827750 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1991. Min Act: -0.1700
Data Index: 4827728 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1991. Min Act: -0.1700
Data Index: 4827751 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1991. Min Act: -0.1700
Data Index: 8182379 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1991. Min Act: -0.1700
Data Index: 2843611 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1678. Min Act: -0.1700
Data Index: 8690125 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1678. Min Act: -0.1698
Data Index: 750345 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1678. Min Act: -0.1700
Data Index: 211923 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1678. Min Act: -0.1700
Data Index: 8127019 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1678. Min Act: -0.1700
Data Index: 7793451 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1991. Min Act: -0.1700
Data Index: 682750 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1991. Min Act: -0.1700
Data Index: 7141673 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1053. Min Act: -0.1700
Data Index: 4301812 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1366. Min Act: -0.1700
Data Index: 4119056 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5116. Min Range: -6.5116
Max Act: 6.1366. Min Act: -0.1700
Data Index: 263702 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19