Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1758. Min Range: -6.1758
Max Act: 6.1758. Min Act: -0.1700
Data Index: 4988025 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1758. Min Range: -6.1758
Max Act: 6.1446. Min Act: -0.1700
Data Index: 7313966 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1758. Min Range: -6.1758
Max Act: 6.0196. Min Act: -0.1700
Data Index: 7592972 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.9571. Min Act: -0.1700
Data Index: 8049093 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.9571. Min Act: -0.1700
Data Index: 3904935 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8946. Min Act: -0.1700
Data Index: 6497919 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.9258. Min Act: -0.1700
Data Index: 4458475 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8633. Min Act: -0.1700
Data Index: 8325773 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8633. Min Act: -0.1700
Data Index: 5148133 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8633. Min Act: -0.1700
Data Index: 6144452 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8008. Min Act: -0.1700
Data Index: 209383 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8008. Min Act: -0.1700
Data Index: 1913838 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.7383. Min Act: -0.1700
Data Index: 3680839 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.7696. Min Act: -0.1700
Data Index: 679255 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8008. Min Act: -0.1700
Data Index: 8483749 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.7696. Min Act: -0.1700
Data Index: 3587602 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.7383. Min Act: -0.1700
Data Index: 1013720 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.7383. Min Act: -0.1700
Data Index: 1209334 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.7383. Min Act: -0.1700
Data Index: 8086581 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.7071. Min Act: -0.1700
Data Index: 3423958 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19