Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 62 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4786. Min Range: -8.4786
Max Act: 8.4786. Min Act: -0.1700
Data Index: 7512489 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4786. Min Range: -8.4786
Max Act: 8.4786. Min Act: -0.1700
Data Index: 3758791 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.7911. Min Act: -0.1700
Data Index: 6248188 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.7599. Min Act: -0.1700
Data Index: 5515764 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.7599. Min Act: -0.1700
Data Index: 344967 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.7599. Min Act: -0.1700
Data Index: 130802 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.7286. Min Act: -0.1700
Data Index: 5703235 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.6661. Min Act: -0.1700
Data Index: 1432513 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.6974. Min Act: -0.1700
Data Index: 181596 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.6974. Min Act: -0.1700
Data Index: 2708747 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.6661. Min Act: -0.1700
Data Index: 6784809 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.6974. Min Act: -0.1700
Data Index: 2833216 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.6349. Min Act: -0.1700
Data Index: 7595824 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.6349. Min Act: -0.1700
Data Index: 4555465 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.6036. Min Act: -0.1700
Data Index: 3785324 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.6036. Min Act: -0.1700
Data Index: 7646070 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.6036. Min Act: -0.1700
Data Index: 4496202 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.6036. Min Act: -0.1700
Data Index: 273022 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.6036. Min Act: -0.1700
Data Index: 5116651 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4786. Min Range: -8.4786
Max Act: 7.5724. Min Act: -0.1700
Data Index: 1685083 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19