Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.2720. Min Act: -0.1700
Data Index: 4385695 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.2249. Min Act: -0.1700
Data Index: 4733853 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.2092. Min Act: -0.1700
Data Index: 4754214 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.1305. Min Act: -0.1700
Data Index: 3947590 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.1147. Min Act: -0.1700
Data Index: 1309184 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0990. Min Act: -0.1700
Data Index: 5193099 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0990. Min Act: -0.1700
Data Index: 8795534 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0832. Min Act: -0.1700
Data Index: 1324413 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0832. Min Act: -0.1700
Data Index: 3970624 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0675. Min Act: -0.1700
Data Index: 3980724 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0517. Min Act: -0.1700
Data Index: 7875501 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0201. Min Act: -0.1700
Data Index: 683940 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2720. Min Range: -3.2720
Max Act: 3.0517. Min Act: -0.1700
Data Index: 2881531 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2720. Min Range: -3.2720
Max Act: 2.9885. Min Act: -0.1700
Data Index: 5997494 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2720. Min Range: -3.2720
Max Act: 2.9885. Min Act: -0.1700
Data Index: 6227318 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2720. Min Range: -3.2720
Max Act: 2.9727. Min Act: -0.1700
Data Index: 4385696 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2720. Min Range: -3.2720
Max Act: 2.9410. Min Act: -0.1700
Data Index: 7959836 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2720. Min Range: -3.2720
Max Act: 2.9410. Min Act: -0.1700
Data Index: 5914915 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2720. Min Range: -3.2720
Max Act: 2.9410. Min Act: -0.1700
Data Index: 6989282 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2720. Min Range: -3.2720
Max Act: 2.9252. Min Act: -0.1700
Data Index: 921512 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19