Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 470 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.2104. Min Act: -0.1700
Data Index: 4008176 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.2104. Min Act: -0.1700
Data Index: 8646677 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.2417. Min Act: -0.1700
Data Index: 3011028 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.1479. Min Act: -0.1700
Data Index: 6860086 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.1479. Min Act: -0.1700
Data Index: 5038285 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.1479. Min Act: -0.1700
Data Index: 4381912 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.1167. Min Act: -0.1700
Data Index: 3011023 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.0854. Min Act: -0.1700
Data Index: 7644167 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.0542. Min Act: -0.1700
Data Index: 6451504 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.0542. Min Act: -0.1700
Data Index: 8290452 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.9604. Min Act: -0.1700
Data Index: 1428051 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.9292. Min Act: -0.1700
Data Index: 4311075 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.9292. Min Act: -0.1700
Data Index: 3300840 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.9292. Min Act: -0.1700
Data Index: 7325749 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.9292. Min Act: -0.1700
Data Index: 2934040 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.8667. Min Act: -0.1700
Data Index: 2409241 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.8667. Min Act: -0.1700
Data Index: 3044357 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.8042. Min Act: -0.1700
Data Index: 81668 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.7729. Min Act: -0.1700
Data Index: 3118174 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.7729. Min Act: -0.1700
Data Index: 3041249 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19