Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4336 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1760. Min Range: -7.1760
Max Act: 7.1760. Min Act: -0.1700
Data Index: 4456039 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1760. Min Range: -7.1760
Max Act: 7.1448. Min Act: -0.1700
Data Index: 273772 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1760. Min Range: -7.1760
Max Act: 7.1135. Min Act: -0.1700
Data Index: 5558851 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.8323. Min Act: -0.1700
Data Index: 5021409 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.8010. Min Act: -0.1700
Data Index: 3185258 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.8010. Min Act: -0.1700
Data Index: 7447849 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.8010. Min Act: -0.1700
Data Index: 6975470 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.7073. Min Act: -0.1700
Data Index: 7575932 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.6760. Min Act: -0.1700
Data Index: 4089886 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.5823. Min Act: -0.1700
Data Index: 2505587 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.5823. Min Act: -0.1700
Data Index: 6691596 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.5510. Min Act: -0.1700
Data Index: 273766 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.5510. Min Act: -0.1700
Data Index: 1850956 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.5510. Min Act: -0.1700
Data Index: 1771971 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.5510. Min Act: -0.1700
Data Index: 5641896 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.5198. Min Act: -0.1700
Data Index: 248416 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.5198. Min Act: -0.1700
Data Index: 5485424 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.5198. Min Act: -0.1700
Data Index: 273765 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.4885. Min Act: -0.1700
Data Index: 62707 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1760. Min Range: -7.1760
Max Act: 6.4885. Min Act: -0.1700
Data Index: 3040206 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19