Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3633 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1697. Min Range: -7.1697
Max Act: 7.1697. Min Act: -0.1700
Data Index: 3610837 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1697. Min Range: -7.1697
Max Act: 7.1072. Min Act: -0.1700
Data Index: 36247 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1697. Min Range: -7.1697
Max Act: 7.0447. Min Act: -0.1700
Data Index: 4519076 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.8572. Min Act: -0.1700
Data Index: 3413800 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.8572. Min Act: -0.1700
Data Index: 2296544 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.8572. Min Act: -0.1700
Data Index: 7551905 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.7947. Min Act: -0.1700
Data Index: 2694245 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.7947. Min Act: -0.1700
Data Index: 5788112 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.7634. Min Act: -0.1700
Data Index: 1047133 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.7009. Min Act: -0.1700
Data Index: 2604967 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.6697. Min Act: -0.1700
Data Index: 8594114 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.6697. Min Act: -0.1700
Data Index: 2937624 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.6697. Min Act: -0.1700
Data Index: 3889419 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.6384. Min Act: -0.1700
Data Index: 3309161 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.6072. Min Act: -0.1700
Data Index: 7282627 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.5759. Min Act: -0.1700
Data Index: 7480203 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.6072. Min Act: -0.1700
Data Index: 5567554 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.6072. Min Act: -0.1700
Data Index: 7254946 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.6072. Min Act: -0.1700
Data Index: 7580069 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1697. Min Range: -7.1697
Max Act: 6.6072. Min Act: -0.1700
Data Index: 6195224 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19