Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2998 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.9837. Min Act: -0.1700
Data Index: 1002382 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.9837. Min Act: -0.1700
Data Index: 6146926 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.8587. Min Act: -0.1700
Data Index: 7324923 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.8587. Min Act: -0.1700
Data Index: 1646747 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.8587. Min Act: -0.1700
Data Index: 828645 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.8274. Min Act: -0.1700
Data Index: 4277762 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.7962. Min Act: -0.1700
Data Index: 3233475 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.7962. Min Act: -0.1700
Data Index: 1658284 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.7649. Min Act: -0.1700
Data Index: 3154815 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.7024. Min Act: -0.1700
Data Index: 7067543 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.7024. Min Act: -0.1700
Data Index: 8273575 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.6712. Min Act: -0.1700
Data Index: 6047487 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.6399. Min Act: -0.1700
Data Index: 1778368 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.6399. Min Act: -0.1700
Data Index: 2242879 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.6712. Min Act: -0.1700
Data Index: 4302456 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.6712. Min Act: -0.1700
Data Index: 6138449 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.6399. Min Act: -0.1700
Data Index: 7169903 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.6399. Min Act: -0.1700
Data Index: 1293166 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.6087. Min Act: -0.1700
Data Index: 3409846 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9837. Min Range: -5.9837
Max Act: 5.6399. Min Act: -0.1700
Data Index: 141466 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19