Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2367 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.8340. Min Act: -0.1700
Data Index: 3911997 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.7715. Min Act: -0.1700
Data Index: 2249257 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.7402. Min Act: -0.1700
Data Index: 1302967 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.7402. Min Act: -0.1700
Data Index: 3527451 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.7089. Min Act: -0.1700
Data Index: 8576806 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6776. Min Act: -0.1700
Data Index: 544048 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6776. Min Act: -0.1700
Data Index: 3768741 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6150. Min Act: -0.1700
Data Index: 3872284 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6150. Min Act: -0.1700
Data Index: 4112233 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6150. Min Act: -0.1700
Data Index: 4331166 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6150. Min Act: -0.1700
Data Index: 7634458 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6150. Min Act: -0.1700
Data Index: 4760272 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6150. Min Act: -0.1700
Data Index: 3131935 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6150. Min Act: -0.1700
Data Index: 8759680 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5837. Min Act: -0.1700
Data Index: 2058612 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5837. Min Act: -0.1700
Data Index: 1824662 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5837. Min Act: -0.1700
Data Index: 4810933 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5837. Min Act: -0.1700
Data Index: 5476773 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5837. Min Act: -0.1700
Data Index: 904010 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5837. Min Act: -0.1700
Data Index: 5500550 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19