Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.2543. Min Act: -0.1700
Data Index: 8646631 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.2386. Min Act: -0.1700
Data Index: 6829405 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.2072. Min Act: -0.1700
Data Index: 7538293 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.1757. Min Act: -0.1700
Data Index: 322342 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.2072. Min Act: -0.1700
Data Index: 1564143 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.1757. Min Act: -0.1700
Data Index: 3160081 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.1443. Min Act: -0.1700
Data Index: 6910260 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.1285. Min Act: -0.1700
Data Index: 1558557 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.1285. Min Act: -0.1700
Data Index: 3971040 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.1128. Min Act: -0.1700
Data Index: 4304198 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.1128. Min Act: -0.1700
Data Index: 6012818 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.1128. Min Act: -0.1700
Data Index: 8160103 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.1128. Min Act: -0.1700
Data Index: 6520466 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.1128. Min Act: -0.1700
Data Index: 4191489 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.1128. Min Act: -0.1700
Data Index: 957608 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.0812. Min Act: -0.1700
Data Index: 6206295 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.0970. Min Act: -0.1700
Data Index: 7797612 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.0970. Min Act: -0.1700
Data Index: 7261226 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.0812. Min Act: -0.1700
Data Index: 1704884 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2543. Min Range: -3.2543
Max Act: 3.0812. Min Act: -0.1700
Data Index: 1962902 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19