Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3183 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.7928. Min Act: -0.1700
Data Index: 7044846 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.8240. Min Act: -0.1700
Data Index: 746159 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6053. Min Act: -0.1700
Data Index: 3297662 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5428. Min Act: -0.1700
Data Index: 8438162 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5115. Min Act: -0.1700
Data Index: 7010663 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.4490. Min Act: -0.1700
Data Index: 6110418 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.4490. Min Act: -0.1700
Data Index: 1963282 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.4178. Min Act: -0.1700
Data Index: 6547132 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3553. Min Act: -0.1700
Data Index: 890406 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3865. Min Act: -0.1700
Data Index: 4738728 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3865. Min Act: -0.1700
Data Index: 8694892 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3865. Min Act: -0.1700
Data Index: 1146904 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3240. Min Act: -0.1700
Data Index: 2967810 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3553. Min Act: -0.1700
Data Index: 2663506 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3553. Min Act: -0.1700
Data Index: 3068481 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3553. Min Act: -0.1700
Data Index: 8383321 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3553. Min Act: -0.1700
Data Index: 796308 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3553. Min Act: -0.1700
Data Index: 2860075 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3240. Min Act: -0.1700
Data Index: 4876339 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.2928. Min Act: -0.1700
Data Index: 1468756 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19