Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 908 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.8765. Min Act: -0.1700
Data Index: 3932085 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.6578. Min Act: -0.1700
Data Index: 5276047 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.5953. Min Act: -0.1700
Data Index: 5832719 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.3765. Min Act: -0.1700
Data Index: 7341787 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.3453. Min Act: -0.1700
Data Index: 5266612 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.2828. Min Act: -0.1700
Data Index: 8512403 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.2515. Min Act: -0.1700
Data Index: 6329079 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.2203. Min Act: -0.1700
Data Index: 631970 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.1890. Min Act: -0.1700
Data Index: 2614521 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.1890. Min Act: -0.1700
Data Index: 7384503 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.1578. Min Act: -0.1700
Data Index: 262928 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.1578. Min Act: -0.1700
Data Index: 7331084 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.1265. Min Act: -0.1700
Data Index: 1253183 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.0953. Min Act: -0.1700
Data Index: 26026 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.0953. Min Act: -0.1700
Data Index: 6067934 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.0640. Min Act: -0.1700
Data Index: 6541302 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.0640. Min Act: -0.1700
Data Index: 4659745 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.0640. Min Act: -0.1700
Data Index: 5575152 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.0640. Min Act: -0.1700
Data Index: 8548417 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8765. Min Range: -5.8765
Max Act: 5.0328. Min Act: -0.1700
Data Index: 6680958 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19