Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2631 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0947. Min Range: -5.0947
Max Act: 5.0947. Min Act: -0.1700
Data Index: 7250349 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0947. Min Range: -5.0947
Max Act: 5.0635. Min Act: -0.1700
Data Index: 7251573 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0947. Min Range: -5.0947
Max Act: 5.0010. Min Act: -0.1700
Data Index: 1905068 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.9072. Min Act: -0.1700
Data Index: 6462578 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.8760. Min Act: -0.1700
Data Index: 8295020 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.8447. Min Act: -0.1700
Data Index: 8153458 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.8447. Min Act: -0.1700
Data Index: 3089232 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.8447. Min Act: -0.1700
Data Index: 3827740 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.8135. Min Act: -0.1700
Data Index: 7991743 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.8135. Min Act: -0.1700
Data Index: 6011631 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.7822. Min Act: -0.1700
Data Index: 8147647 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.7510. Min Act: -0.1700
Data Index: 6404836 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.7510. Min Act: -0.1700
Data Index: 6233205 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.7510. Min Act: -0.1700
Data Index: 8384944 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.7197. Min Act: -0.1700
Data Index: 7394248 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.6885. Min Act: -0.1700
Data Index: 1845665 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.6885. Min Act: -0.1700
Data Index: 7343176 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.6885. Min Act: -0.1700
Data Index: 92027 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.6572. Min Act: -0.1700
Data Index: 3013456 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0947. Min Range: -5.0947
Max Act: 4.6572. Min Act: -0.1700
Data Index: 5675821 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19