Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1772 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.9941. Min Act: -0.1700
Data Index: 2354283 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.9004. Min Act: -0.1699
Data Index: 2237307 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.8066. Min Act: -0.1700
Data Index: 2759185 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.8066. Min Act: -0.1700
Data Index: 2349619 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.7441. Min Act: -0.1700
Data Index: 7345477 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.7441. Min Act: -0.1700
Data Index: 8305039 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.7441. Min Act: -0.1700
Data Index: 4509245 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.7441. Min Act: -0.1700
Data Index: 1312110 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.7129. Min Act: -0.1700
Data Index: 1019837 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.7129. Min Act: -0.1700
Data Index: 7474852 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.7129. Min Act: -0.1700
Data Index: 5267270 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.6816. Min Act: -0.1700
Data Index: 1228087 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.6816. Min Act: -0.1700
Data Index: 974476 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.6816. Min Act: -0.1700
Data Index: 1401178 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.6504. Min Act: -0.1700
Data Index: 6870766 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.6504. Min Act: -0.1700
Data Index: 8181587 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.6504. Min Act: -0.1700
Data Index: 2382911 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.6504. Min Act: -0.1700
Data Index: 1567098 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.6191. Min Act: -0.1700
Data Index: 519628 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9941. Min Range: -5.9941
Max Act: 5.6191. Min Act: -0.1700
Data Index: 1015030 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19