Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2586 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1600. Min Range: -7.1600
Max Act: 7.1600. Min Act: -0.1700
Data Index: 1053416 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1600. Min Range: -7.1600
Max Act: 7.0350. Min Act: -0.1700
Data Index: 5331549 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.8475. Min Act: -0.1700
Data Index: 8462658 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.7850. Min Act: -0.1700
Data Index: 6246370 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.6912. Min Act: -0.1700
Data Index: 6614765 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.6600. Min Act: -0.1700
Data Index: 3600615 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.6600. Min Act: -0.1700
Data Index: 5709540 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.6912. Min Act: -0.1700
Data Index: 28227 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.6912. Min Act: -0.1700
Data Index: 6557367 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.6600. Min Act: -0.1700
Data Index: 5390288 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.5662. Min Act: -0.1700
Data Index: 7114176 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.5662. Min Act: -0.1700
Data Index: 5516037 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.5350. Min Act: -0.1700
Data Index: 956566 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.5037. Min Act: -0.1700
Data Index: 8256301 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.5037. Min Act: -0.1700
Data Index: 4071320 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.5037. Min Act: -0.1700
Data Index: 538476 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.4412. Min Act: -0.1700
Data Index: 5348779 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.4725. Min Act: -0.1700
Data Index: 4489166 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.4100. Min Act: -0.1700
Data Index: 3797026 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1600. Min Range: -7.1600
Max Act: 6.4412. Min Act: -0.1700
Data Index: 7287826 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19