Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5252 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.6199. Min Act: -0.1700
Data Index: 6952038 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.5887. Min Act: -0.1700
Data Index: 487910 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.5887. Min Act: -0.1700
Data Index: 7183087 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.5262. Min Act: -0.1700
Data Index: 1342376 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.3074. Min Act: -0.1700
Data Index: 4977006 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.3074. Min Act: -0.1700
Data Index: 2035096 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.2449. Min Act: -0.1700
Data Index: 1813739 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.2449. Min Act: -0.1700
Data Index: 2107453 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.2761. Min Act: -0.1700
Data Index: 1837751 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.1824. Min Act: -0.1700
Data Index: 1584749 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.1824. Min Act: -0.1700
Data Index: 2407087 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.1824. Min Act: -0.1700
Data Index: 608698 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.1824. Min Act: -0.1700
Data Index: 1821338 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.1824. Min Act: -0.1700
Data Index: 7239822 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.1824. Min Act: -0.1700
Data Index: 6941239 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.1511. Min Act: -0.1700
Data Index: 6520920 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.1511. Min Act: -0.1700
Data Index: 3013886 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.1511. Min Act: -0.1700
Data Index: 6364530 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.0886. Min Act: -0.1700
Data Index: 5338015 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6199. Min Range: -4.6199
Max Act: 4.1199. Min Act: -0.1700
Data Index: 4700674 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19