Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1768 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.7330. Min Act: -0.1700
Data Index: 3828421 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.5768. Min Act: -0.1700
Data Index: 3650983 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.3893. Min Act: -0.1700
Data Index: 5400624 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.2643. Min Act: -0.1700
Data Index: 5704902 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.2018. Min Act: -0.1700
Data Index: 313342 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.2018. Min Act: -0.1700
Data Index: 8717105 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.1705. Min Act: -0.1700
Data Index: 8402734 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.1393. Min Act: -0.1700
Data Index: 8471440 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.1393. Min Act: -0.1700
Data Index: 7426321 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.1080. Min Act: -0.1700
Data Index: 7075273 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.0768. Min Act: -0.1700
Data Index: 5285633 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.0768. Min Act: -0.1700
Data Index: 149897 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.0768. Min Act: -0.1700
Data Index: 3907309 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.0455. Min Act: -0.1700
Data Index: 2679958 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.0455. Min Act: -0.1700
Data Index: 4794793 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.0143. Min Act: -0.1700
Data Index: 8371954 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.0455. Min Act: -0.1700
Data Index: 4184344 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7330. Min Range: -6.7330
Max Act: 6.0143. Min Act: -0.1700
Data Index: 7232810 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7330. Min Range: -6.7330
Max Act: 5.9830. Min Act: -0.1700
Data Index: 1253345 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7330. Min Range: -6.7330
Max Act: 5.9830. Min Act: -0.1700
Data Index: 1350509 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19