Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5339 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.6716. Min Act: -0.1700
Data Index: 5599990 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.4528. Min Act: -0.1700
Data Index: 6959330 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.4216. Min Act: -0.1700
Data Index: 1724043 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.4216. Min Act: -0.1700
Data Index: 4577342 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.3903. Min Act: -0.1700
Data Index: 6143491 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.3278. Min Act: -0.1700
Data Index: 6358502 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.2966. Min Act: -0.1700
Data Index: 3821077 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.3278. Min Act: -0.1700
Data Index: 4916727 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.2966. Min Act: -0.1700
Data Index: 8016607 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.2653. Min Act: -0.1700
Data Index: 7029813 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.2653. Min Act: -0.1700
Data Index: 8737376 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.2341. Min Act: -0.1700
Data Index: 691202 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.2341. Min Act: -0.1700
Data Index: 1508760 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.2341. Min Act: -0.1700
Data Index: 7098035 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.2341. Min Act: -0.1700
Data Index: 2012128 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.2028. Min Act: -0.1700
Data Index: 428981 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.1716. Min Act: -0.1700
Data Index: 7619676 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.1716. Min Act: -0.1700
Data Index: 7989687 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.1716. Min Act: -0.1700
Data Index: 7449911 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6716. Min Range: -5.6716
Max Act: 5.1403. Min Act: -0.1700
Data Index: 2110814 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19