Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 816 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.8281. Min Act: -0.1700
Data Index: 439532 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.5781. Min Act: -0.1700
Data Index: 205323 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.5469. Min Act: -0.1700
Data Index: 3716023 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.4531. Min Act: -0.1700
Data Index: 7938647 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.4219. Min Act: -0.1700
Data Index: 205127 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.4219. Min Act: -0.1700
Data Index: 1551208 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.3906. Min Act: -0.1700
Data Index: 630478 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.4219. Min Act: -0.1700
Data Index: 4372557 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.4219. Min Act: -0.1700
Data Index: 2802146 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.3594. Min Act: -0.1700
Data Index: 4286426 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.3281. Min Act: -0.1700
Data Index: 4286425 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.3281. Min Act: -0.1700
Data Index: 2035759 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.2969. Min Act: -0.1700
Data Index: 6474647 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.2969. Min Act: -0.1700
Data Index: 7311224 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.2031. Min Act: -0.1700
Data Index: 349612 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.1406. Min Act: -0.1700
Data Index: 8500836 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.1406. Min Act: -0.1700
Data Index: 7514658 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.1406. Min Act: -0.1700
Data Index: 186451 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.1406. Min Act: -0.1700
Data Index: 186450 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8281. Min Range: -5.8281
Max Act: 5.1094. Min Act: -0.1700
Data Index: 738716 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19