Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1470 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.8203. Min Act: -0.1700
Data Index: 5354844 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.7265. Min Act: -0.1700
Data Index: 847057 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.6328. Min Act: -0.1700
Data Index: 637367 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.6640. Min Act: -0.1700
Data Index: 6878303 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.6328. Min Act: -0.1700
Data Index: 7575697 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.6328. Min Act: -0.1700
Data Index: 5407386 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.6328. Min Act: -0.1700
Data Index: 6026135 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.5703. Min Act: -0.1700
Data Index: 4663244 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.5703. Min Act: -0.1700
Data Index: 1255032 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.5390. Min Act: -0.1700
Data Index: 7853390 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.5390. Min Act: -0.1700
Data Index: 4361707 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.5078. Min Act: -0.1700
Data Index: 622846 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.5078. Min Act: -0.1700
Data Index: 4841067 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.5078. Min Act: -0.1700
Data Index: 1153806 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.5078. Min Act: -0.1700
Data Index: 847055 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.5078. Min Act: -0.1700
Data Index: 1631817 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.4765. Min Act: -0.1700
Data Index: 7154843 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.4765. Min Act: -0.1700
Data Index: 2875516 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.4765. Min Act: -0.1700
Data Index: 3034755 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8203. Min Range: -5.8203
Max Act: 5.4765. Min Act: -0.1700
Data Index: 5358999 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19