Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3219 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5111. Min Range: -5.5111
Max Act: 5.5111. Min Act: -0.1700
Data Index: 5125300 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5111. Min Range: -5.5111
Max Act: 5.1361. Min Act: -0.1700
Data Index: 8240898 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5111. Min Range: -5.5111
Max Act: 5.1049. Min Act: -0.1700
Data Index: 2600797 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5111. Min Range: -5.5111
Max Act: 5.0736. Min Act: -0.1700
Data Index: 4473045 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5111. Min Range: -5.5111
Max Act: 5.0424. Min Act: -0.1700
Data Index: 7556163 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5111. Min Range: -5.5111
Max Act: 5.0424. Min Act: -0.1700
Data Index: 7790160 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.9799. Min Act: -0.1700
Data Index: 7772829 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.9799. Min Act: -0.1700
Data Index: 226455 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.9799. Min Act: -0.1700
Data Index: 4681948 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.9799. Min Act: -0.1700
Data Index: 7441212 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.9799. Min Act: -0.1700
Data Index: 7426939 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.9486. Min Act: -0.1700
Data Index: 5504648 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.9486. Min Act: -0.1700
Data Index: 232943 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.9174. Min Act: -0.1700
Data Index: 3867820 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.9174. Min Act: -0.1700
Data Index: 1274942 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.9174. Min Act: -0.1700
Data Index: 3541451 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.8549. Min Act: -0.1700
Data Index: 8545844 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.8549. Min Act: -0.1700
Data Index: 4063668 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.8549. Min Act: -0.1700
Data Index: 401763 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5111. Min Range: -5.5111
Max Act: 4.8549. Min Act: -0.1700
Data Index: 7399378 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19