Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.8544. Min Act: -0.1700
Data Index: 2443748 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.8544. Min Act: -0.1700
Data Index: 8493568 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.6982. Min Act: -0.1700
Data Index: 3847103 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.6982. Min Act: -0.1700
Data Index: 3243417 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.6044. Min Act: -0.1700
Data Index: 1536967 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.5419. Min Act: -0.1700
Data Index: 3454432 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.5419. Min Act: -0.1700
Data Index: 3502965 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.5732. Min Act: -0.1700
Data Index: 1444589 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.5107. Min Act: -0.1700
Data Index: 3290719 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.5107. Min Act: -0.1700
Data Index: 5778755 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.4794. Min Act: -0.1700
Data Index: 8100240 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.4794. Min Act: -0.1700
Data Index: 3480596 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.4794. Min Act: -0.1700
Data Index: 3470484 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.4794. Min Act: -0.1700
Data Index: 6432353 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.4794. Min Act: -0.1700
Data Index: 1357085 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.4169. Min Act: -0.1700
Data Index: 5560344 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.4169. Min Act: -0.1700
Data Index: 528875 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.4794. Min Act: -0.1700
Data Index: 2389364 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.4169. Min Act: -0.1700
Data Index: 5322254 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8544. Min Range: -5.8544
Max Act: 5.4169. Min Act: -0.1700
Data Index: 2810065 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19