Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3462 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.3875. Min Act: -0.1700
Data Index: 186644 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.3875. Min Act: -0.1700
Data Index: 4704633 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.3250. Min Act: -0.1700
Data Index: 5444359 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.2625. Min Act: -0.1700
Data Index: 7901004 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.2937. Min Act: -0.1700
Data Index: 4423551 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.2312. Min Act: -0.1698
Data Index: 5374996 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.2312. Min Act: -0.1700
Data Index: 7509901 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.2312. Min Act: -0.1700
Data Index: 7043590 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.0750. Min Act: -0.1700
Data Index: 7976530 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.0750. Min Act: -0.1700
Data Index: 4214276 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.0437. Min Act: -0.1700
Data Index: 841397 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.0437. Min Act: -0.1700
Data Index: 4892324 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.0437. Min Act: -0.1700
Data Index: 5444360 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.0437. Min Act: -0.1700
Data Index: 7746122 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.0437. Min Act: -0.1700
Data Index: 2080111 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.0437. Min Act: -0.1700
Data Index: 7719085 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.0125. Min Act: -0.1700
Data Index: 4054378 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3875. Min Range: -6.3875
Max Act: 5.9812. Min Act: -0.1700
Data Index: 959903 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.0125. Min Act: -0.1700
Data Index: 7275099 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3875. Min Range: -6.3875
Max Act: 6.0437. Min Act: -0.1700
Data Index: 5640882 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19