Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3812 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4292. Min Range: -7.4292
Max Act: 7.4292. Min Act: -0.1700
Data Index: 8624850 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4292. Min Range: -7.4292
Max Act: 7.2417. Min Act: -0.1700
Data Index: 3671545 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4292. Min Range: -7.4292
Max Act: 7.2417. Min Act: -0.1700
Data Index: 835747 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4292. Min Range: -7.4292
Max Act: 7.1167. Min Act: -0.1700
Data Index: 7972360 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4292. Min Range: -7.4292
Max Act: 7.0855. Min Act: -0.1700
Data Index: 7259434 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4292. Min Range: -7.4292
Max Act: 7.0542. Min Act: -0.1700
Data Index: 6355166 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4292. Min Range: -7.4292
Max Act: 7.0230. Min Act: -0.1700
Data Index: 8178029 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4292. Min Range: -7.4292
Max Act: 6.9917. Min Act: -0.1700
Data Index: 2920615 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4292. Min Range: -7.4292
Max Act: 6.8980. Min Act: -0.1700
Data Index: 519669 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4292. Min Range: -7.4292
Max Act: 6.8980. Min Act: -0.1700
Data Index: 4674350 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4292. Min Range: -7.4292
Max Act: 6.8980. Min Act: -0.1700
Data Index: 8726896 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4292. Min Range: -7.4292
Max Act: 6.9292. Min Act: -0.1700
Data Index: 7799637 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4292. Min Range: -7.4292
Max Act: 6.8980. Min Act: -0.1700
Data Index: 7648868 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4292. Min Range: -7.4292
Max Act: 6.8980. Min Act: -0.1700
Data Index: 6598224 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4292. Min Range: -7.4292
Max Act: 6.9292. Min Act: -0.1700
Data Index: 3475215 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4292. Min Range: -7.4292
Max Act: 6.8355. Min Act: -0.1700
Data Index: 4391854 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4292. Min Range: -7.4292
Max Act: 6.8355. Min Act: -0.1700
Data Index: 4175167 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4292. Min Range: -7.4292
Max Act: 6.8355. Min Act: -0.1700
Data Index: 8641285 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4292. Min Range: -7.4292
Max Act: 6.8355. Min Act: -0.1700
Data Index: 3679417 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4292. Min Range: -7.4292
Max Act: 6.8042. Min Act: -0.1700
Data Index: 2573800 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19