Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4713 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0624. Min Range: -6.0624
Max Act: 6.0624. Min Act: -0.1700
Data Index: 7549556 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.5936. Min Act: -0.1700
Data Index: 3584794 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.4999. Min Act: -0.1700
Data Index: 7377822 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.3436. Min Act: -0.1700
Data Index: 1197757 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.3124. Min Act: -0.1700
Data Index: 1010703 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.2186. Min Act: -0.1700
Data Index: 7628442 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.1874. Min Act: -0.1700
Data Index: 2207330 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.1874. Min Act: -0.1700
Data Index: 7373919 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.1874. Min Act: -0.1700
Data Index: 6996898 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.1249. Min Act: -0.1700
Data Index: 3092987 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.1561. Min Act: -0.1700
Data Index: 4590780 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.1561. Min Act: -0.1700
Data Index: 6773248 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.1561. Min Act: -0.1700
Data Index: 6958593 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.1561. Min Act: -0.1700
Data Index: 3437078 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.1249. Min Act: -0.1700
Data Index: 4311225 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.1249. Min Act: -0.1700
Data Index: 2550747 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.0936. Min Act: -0.1700
Data Index: 5919132 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.1249. Min Act: -0.1700
Data Index: 4895995 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.0936. Min Act: -0.1700
Data Index: 5511008 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0624. Min Range: -6.0624
Max Act: 5.0936. Min Act: -0.1700
Data Index: 2382176 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19