Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4818 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.8993. Min Act: -0.1700
Data Index: 8428953 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.8368. Min Act: -0.1700
Data Index: 7262187 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.7743. Min Act: -0.1700
Data Index: 689418 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.5243. Min Act: -0.1700
Data Index: 7501045 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.4306. Min Act: -0.1700
Data Index: 2109288 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.3368. Min Act: -0.1700
Data Index: 6266500 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.3056. Min Act: -0.1700
Data Index: 5648697 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.3056. Min Act: -0.1700
Data Index: 728691 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.3056. Min Act: -0.1700
Data Index: 1021247 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.2431. Min Act: -0.1700
Data Index: 659576 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.2431. Min Act: -0.1700
Data Index: 5885649 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.2431. Min Act: -0.1700
Data Index: 8394004 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.1806. Min Act: -0.1700
Data Index: 8665691 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.1806. Min Act: -0.1700
Data Index: 8056088 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.1806. Min Act: -0.1700
Data Index: 2025720 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.1181. Min Act: -0.1700
Data Index: 8395149 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.1493. Min Act: -0.1700
Data Index: 6172229 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.1181. Min Act: -0.1700
Data Index: 4850983 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.1181. Min Act: -0.1700
Data Index: 1405026 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8993. Min Range: -6.8993
Max Act: 6.1181. Min Act: -0.1700
Data Index: 6462199 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19