Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5471 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.9922. Min Act: -0.1700
Data Index: 6874830 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.8672. Min Act: -0.1700
Data Index: 4096625 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.8360. Min Act: -0.1700
Data Index: 8550037 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.7735. Min Act: -0.1700
Data Index: 3780684 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.7422. Min Act: -0.1700
Data Index: 3137947 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.7422. Min Act: -0.1700
Data Index: 3521286 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.7422. Min Act: -0.1700
Data Index: 8785225 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.7110. Min Act: -0.1700
Data Index: 6586073 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.6797. Min Act: -0.1700
Data Index: 769975 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.7110. Min Act: -0.1700
Data Index: 8008750 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.7110. Min Act: -0.1700
Data Index: 1838676 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.6797. Min Act: -0.1700
Data Index: 2791259 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.6797. Min Act: -0.1700
Data Index: 416877 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.6797. Min Act: -0.1700
Data Index: 8533984 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.6797. Min Act: -0.1700
Data Index: 4245449 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.6797. Min Act: -0.1700
Data Index: 5910175 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.6485. Min Act: -0.1700
Data Index: 7608755 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.6485. Min Act: -0.1700
Data Index: 1256252 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.6485. Min Act: -0.1700
Data Index: 455175 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9922. Min Range: -5.9922
Max Act: 5.6172. Min Act: -0.1700
Data Index: 961050 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19