Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3818 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.2704. Min Act: -0.1700
Data Index: 6820825 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.2704. Min Act: -0.1700
Data Index: 1755964 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.2233. Min Act: -0.1699
Data Index: 6004059 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.2390. Min Act: -0.1700
Data Index: 863811 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.2390. Min Act: -0.1700
Data Index: 8075998 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1918. Min Act: -0.1698
Data Index: 6462296 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1918. Min Act: -0.1698
Data Index: 8613558 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.2075. Min Act: -0.1700
Data Index: 4715274 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1918. Min Act: -0.1700
Data Index: 5029904 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1761. Min Act: -0.1700
Data Index: 5321536 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1604. Min Act: -0.1700
Data Index: 8083663 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1604. Min Act: -0.1700
Data Index: 4484124 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1604. Min Act: -0.1700
Data Index: 3952817 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1761. Min Act: -0.1700
Data Index: 6979082 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1604. Min Act: -0.1700
Data Index: 7638529 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1446. Min Act: -0.1700
Data Index: 5860277 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1446. Min Act: -0.1700
Data Index: 7929904 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1446. Min Act: -0.1700
Data Index: 4879958 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1446. Min Act: -0.1700
Data Index: 4243442 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2704. Min Range: -3.2704
Max Act: 3.1289. Min Act: -0.1700
Data Index: 1997911 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19