Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 719 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3922. Min Range: -6.3922
Max Act: 6.3922. Min Act: -0.1700
Data Index: 7173254 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3922. Min Range: -6.3922
Max Act: 6.1422. Min Act: -0.1700
Data Index: 3103492 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3922. Min Range: -6.3922
Max Act: 6.0797. Min Act: -0.1700
Data Index: 4052915 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.9860. Min Act: -0.1700
Data Index: 3866587 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.9860. Min Act: -0.1700
Data Index: 5822575 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3922. Min Range: -6.3922
Max Act: 6.0172. Min Act: -0.1700
Data Index: 4766510 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.9547. Min Act: -0.1700
Data Index: 1744779 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.9547. Min Act: -0.1700
Data Index: 5584368 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.9547. Min Act: -0.1700
Data Index: 8349537 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.9860. Min Act: -0.1700
Data Index: 8812080 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.8922. Min Act: -0.1700
Data Index: 3783573 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.8922. Min Act: -0.1700
Data Index: 929749 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.8297. Min Act: -0.1700
Data Index: 7253738 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.8297. Min Act: -0.1700
Data Index: 2949169 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.8297. Min Act: -0.1700
Data Index: 4675407 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.8297. Min Act: -0.1700
Data Index: 3992969 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.7985. Min Act: -0.1700
Data Index: 8300535 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.8297. Min Act: -0.1700
Data Index: 8131996 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.8297. Min Act: -0.1700
Data Index: 5092324 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3922. Min Range: -6.3922
Max Act: 5.7985. Min Act: -0.1700
Data Index: 4564223 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19