Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2095 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1218. Min Range: -8.1218
Max Act: 8.1218. Min Act: -0.1700
Data Index: 6558494 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.6843. Min Act: -0.1700
Data Index: 4645539 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.5906. Min Act: -0.1700
Data Index: 6270440 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.5593. Min Act: -0.1700
Data Index: 7905976 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.5593. Min Act: -0.1700
Data Index: 3129133 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.4343. Min Act: -0.1700
Data Index: 5929134 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.4343. Min Act: -0.1700
Data Index: 4064347 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.3718. Min Act: -0.1700
Data Index: 2901525 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.3718. Min Act: -0.1700
Data Index: 2264088 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.3093. Min Act: -0.1700
Data Index: 1457655 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.2781. Min Act: -0.1700
Data Index: 2654759 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.2468. Min Act: -0.1700
Data Index: 5044932 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.2156. Min Act: -0.1700
Data Index: 3302963 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.1843. Min Act: -0.1700
Data Index: 4691298 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.1843. Min Act: -0.1700
Data Index: 5961694 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.1531. Min Act: -0.1700
Data Index: 4052988 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.1843. Min Act: -0.1700
Data Index: 1584298 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.1843. Min Act: -0.1700
Data Index: 1525736 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.1531. Min Act: -0.1700
Data Index: 4496174 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.1218. Min Act: -0.1700
Data Index: 1560162 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19