Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0676. Min Range: -6.0676
Max Act: 6.0676. Min Act: -0.1700
Data Index: 1935856 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.8488. Min Act: -0.1700
Data Index: 4516120 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.7863. Min Act: -0.1700
Data Index: 3062671 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.7238. Min Act: -0.1700
Data Index: 1595797 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.7551. Min Act: -0.1700
Data Index: 1127339 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.6613. Min Act: -0.1700
Data Index: 4322698 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.6613. Min Act: -0.1700
Data Index: 6644642 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.5988. Min Act: -0.1700
Data Index: 6580964 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.5988. Min Act: -0.1700
Data Index: 1979376 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.6301. Min Act: -0.1700
Data Index: 7436124 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.5363. Min Act: -0.1700
Data Index: 2169659 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.5363. Min Act: -0.1700
Data Index: 5192094 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.5363. Min Act: -0.1700
Data Index: 6012704 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.5051. Min Act: -0.1700
Data Index: 5949072 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.5051. Min Act: -0.1700
Data Index: 5289689 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.4738. Min Act: -0.1700
Data Index: 3444513 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.4426. Min Act: -0.1700
Data Index: 3398977 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.4113. Min Act: -0.1700
Data Index: 2879290 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.4426. Min Act: -0.1700
Data Index: 1320964 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0676. Min Range: -6.0676
Max Act: 5.4113. Min Act: -0.1700
Data Index: 4626618 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19