Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3951 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.5031. Min Act: -0.1700
Data Index: 1177 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.4093. Min Act: -0.1700
Data Index: 797905 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.3781. Min Act: -0.1700
Data Index: 7948280 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.3781. Min Act: -0.1680
Data Index: 6080325 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.3468. Min Act: -0.1679
Data Index: 3798124 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.3468. Min Act: -0.1698
Data Index: 6070922 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.3468. Min Act: -0.1700
Data Index: 5492556 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.3468. Min Act: -0.1700
Data Index: 5391361 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.3468. Min Act: -0.1700
Data Index: 5189638 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.3468. Min Act: -0.1700
Data Index: 603994 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.3468. Min Act: -0.1700
Data Index: 1897768 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.3156. Min Act: -0.1700
Data Index: 206273 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.3156. Min Act: -0.1700
Data Index: 4069687 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.2843. Min Act: -0.1700
Data Index: 242919 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.2843. Min Act: -0.1697
Data Index: 1148303 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.2843. Min Act: -0.1694
Data Index: 112610 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.2843. Min Act: -0.1700
Data Index: 577922 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.2843. Min Act: -0.1696
Data Index: 1260880 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.2843. Min Act: -0.1700
Data Index: 883514 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5031. Min Range: -5.5031
Max Act: 5.2843. Min Act: -0.1698
Data Index: 286753 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19