Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.3159. Min Act: -0.1700
Data Index: 2330303 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.2374. Min Act: -0.1700
Data Index: 456052 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.1745. Min Act: -0.1700
Data Index: 103457 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0800. Min Act: -0.1700
Data Index: 8298532 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0642. Min Act: -0.1700
Data Index: 6795706 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0168. Min Act: -0.1700
Data Index: 8536453 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0326. Min Act: -0.1700
Data Index: 8536455 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0326. Min Act: -0.1700
Data Index: 3671684 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0326. Min Act: -0.1700
Data Index: 2898421 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0168. Min Act: -0.1700
Data Index: 8536454 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0326. Min Act: -0.1700
Data Index: 2999584 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0168. Min Act: -0.1700
Data Index: 6662806 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0326. Min Act: -0.1700
Data Index: 8713348 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0010. Min Act: -0.1700
Data Index: 4131967 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0010. Min Act: -0.1700
Data Index: 6455938 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0010. Min Act: -0.1700
Data Index: 8505215 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3159. Min Range: -3.3159
Max Act: 3.0010. Min Act: -0.1700
Data Index: 3423995 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3159. Min Range: -3.3159
Max Act: 2.9852. Min Act: -0.1700
Data Index: 5052435 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3159. Min Range: -3.3159
Max Act: 2.9852. Min Act: -0.1700
Data Index: 1150283 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3159. Min Range: -3.3159
Max Act: 2.9694. Min Act: -0.1700
Data Index: 6822205 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19