Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2672 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.7679. Min Act: -0.1700
Data Index: 1950384 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.6429. Min Act: -0.1700
Data Index: 3839491 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.5179. Min Act: -0.1700
Data Index: 2669324 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.3929. Min Act: -0.1700
Data Index: 1525983 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.3929. Min Act: -0.1700
Data Index: 298543 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.2679. Min Act: -0.1700
Data Index: 7205097 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.3304. Min Act: -0.1700
Data Index: 1839711 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.2679. Min Act: -0.1700
Data Index: 298541 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.1429. Min Act: -0.1700
Data Index: 5311288 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.0804. Min Act: -0.1700
Data Index: 4409707 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.0804. Min Act: -0.1700
Data Index: 1587298 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.1429. Min Act: -0.1700
Data Index: 1550407 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.0491. Min Act: -0.1700
Data Index: 8032852 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.0491. Min Act: -0.1700
Data Index: 2761017 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7679. Min Range: -8.7679
Max Act: 7.9866. Min Act: -0.1700
Data Index: 8539128 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7679. Min Range: -8.7679
Max Act: 7.9866. Min Act: -0.1700
Data Index: 5813185 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.0179. Min Act: -0.1700
Data Index: 4624559 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7679. Min Range: -8.7679
Max Act: 8.0179. Min Act: -0.1700
Data Index: 59344 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7679. Min Range: -8.7679
Max Act: 7.9866. Min Act: -0.1700
Data Index: 4809489 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7679. Min Range: -8.7679
Max Act: 7.9866. Min Act: -0.1700
Data Index: 4934865 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19