Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 518 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.3892. Min Act: -0.1700
Data Index: 2882365 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.3267. Min Act: -0.1700
Data Index: 3969692 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.2642. Min Act: -0.1700
Data Index: 2485238 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.3267. Min Act: -0.1700
Data Index: 7283966 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.2330. Min Act: -0.1700
Data Index: 1936752 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.2017. Min Act: -0.1700
Data Index: 3870996 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.2017. Min Act: -0.1700
Data Index: 4775659 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.2017. Min Act: -0.1700
Data Index: 37953 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.2330. Min Act: -0.1700
Data Index: 4282918 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.2017. Min Act: -0.1700
Data Index: 4998187 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.1705. Min Act: -0.1700
Data Index: 2711563 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.1392. Min Act: -0.1700
Data Index: 3828019 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.1392. Min Act: -0.1700
Data Index: 7201473 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.1080. Min Act: -0.1700
Data Index: 5930020 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.1080. Min Act: -0.1700
Data Index: 6320660 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.0767. Min Act: -0.1700
Data Index: 5045497 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.0767. Min Act: -0.1700
Data Index: 6559995 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.0455. Min Act: -0.1700
Data Index: 1595100 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.0455. Min Act: -0.1700
Data Index: 3168110 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.0767. Min Act: -0.1700
Data Index: 6502259 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19