Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2354 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.5350. Min Act: -0.1700
Data Index: 7314262 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.5350. Min Act: -0.1700
Data Index: 3486733 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.5350. Min Act: -0.1700
Data Index: 2406558 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.4725. Min Act: -0.1700
Data Index: 2436443 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.4413. Min Act: -0.1700
Data Index: 1062955 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.4413. Min Act: -0.1700
Data Index: 8064458 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.4100. Min Act: -0.1700
Data Index: 168573 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.3788. Min Act: -0.1700
Data Index: 4480758 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.4100. Min Act: -0.1700
Data Index: 4735281 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.3163. Min Act: -0.1700
Data Index: 297946 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.2850. Min Act: -0.1700
Data Index: 5813915 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.2850. Min Act: -0.1700
Data Index: 7460463 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.2850. Min Act: -0.1700
Data Index: 1445479 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.2850. Min Act: -0.1700
Data Index: 944166 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.2538. Min Act: -0.1700
Data Index: 182070 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.2225. Min Act: -0.1700
Data Index: 8173434 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.2538. Min Act: -0.1700
Data Index: 7715807 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.2538. Min Act: -0.1700
Data Index: 5346730 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.2225. Min Act: -0.1700
Data Index: 6910122 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5350. Min Range: -7.5350
Max Act: 7.1913. Min Act: -0.1700
Data Index: 3929677 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19