Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3961 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.9101. Min Act: -0.1700
Data Index: 4482633 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.9726. Min Act: -0.1700
Data Index: 6086232 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.7851. Min Act: -0.1700
Data Index: 7612927 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.7226. Min Act: -0.1700
Data Index: 118071 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.6913. Min Act: -0.1700
Data Index: 6118172 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.5976. Min Act: -0.1700
Data Index: 5209095 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.5351. Min Act: -0.1700
Data Index: 7660774 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.5663. Min Act: -0.1700
Data Index: 3586228 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.5351. Min Act: -0.1700
Data Index: 7314016 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.5351. Min Act: -0.1700
Data Index: 6070882 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.5038. Min Act: -0.1700
Data Index: 5050766 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.4726. Min Act: -0.1700
Data Index: 3137187 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.4726. Min Act: -0.1700
Data Index: 5966903 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.4726. Min Act: -0.1700
Data Index: 5966888 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.4726. Min Act: -0.1700
Data Index: 6406821 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.4413. Min Act: -0.1700
Data Index: 5740838 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.3788. Min Act: -0.1700
Data Index: 7660772 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.4101. Min Act: -0.1700
Data Index: 8141596 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.3788. Min Act: -0.1700
Data Index: 6976627 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9726. Min Range: -7.9726
Max Act: 7.3476. Min Act: -0.1700
Data Index: 5966902 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19