Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5807 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6262. Min Range: -7.6262
Max Act: 7.6262. Min Act: -0.1700
Data Index: 4088310 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6262. Min Range: -7.6262
Max Act: 7.2512. Min Act: -0.1700
Data Index: 7198060 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6262. Min Range: -7.6262
Max Act: 7.2512. Min Act: -0.1700
Data Index: 2147331 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6262. Min Range: -7.6262
Max Act: 7.1887. Min Act: -0.1700
Data Index: 2491946 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6262. Min Range: -7.6262
Max Act: 7.0949. Min Act: -0.1700
Data Index: 5443120 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6262. Min Range: -7.6262
Max Act: 7.0324. Min Act: -0.1700
Data Index: 8009421 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6262. Min Range: -7.6262
Max Act: 7.0324. Min Act: -0.1700
Data Index: 32747 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6262. Min Range: -7.6262
Max Act: 7.0324. Min Act: -0.1700
Data Index: 8757646 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6262. Min Range: -7.6262
Max Act: 7.0012. Min Act: -0.1700
Data Index: 7220029 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6262. Min Range: -7.6262
Max Act: 6.9387. Min Act: -0.1700
Data Index: 7878645 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6262. Min Range: -7.6262
Max Act: 6.9699. Min Act: -0.1700
Data Index: 2347086 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6262. Min Range: -7.6262
Max Act: 6.9699. Min Act: -0.1700
Data Index: 524477 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6262. Min Range: -7.6262
Max Act: 6.9699. Min Act: -0.1700
Data Index: 5189672 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6262. Min Range: -7.6262
Max Act: 6.9699. Min Act: -0.1700
Data Index: 775059 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6262. Min Range: -7.6262
Max Act: 6.9699. Min Act: -0.1700
Data Index: 7052944 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6262. Min Range: -7.6262
Max Act: 6.9074. Min Act: -0.1700
Data Index: 4892255 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6262. Min Range: -7.6262
Max Act: 6.9074. Min Act: -0.1700
Data Index: 5994328 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6262. Min Range: -7.6262
Max Act: 6.8762. Min Act: -0.1700
Data Index: 1953924 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6262. Min Range: -7.6262
Max Act: 6.8449. Min Act: -0.1700
Data Index: 2361123 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6262. Min Range: -7.6262
Max Act: 6.8449. Min Act: -0.1700
Data Index: 2308560 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19