Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 650 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.8606. Min Act: -0.1700
Data Index: 1536788 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.8606. Min Act: -0.1700
Data Index: 8171565 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.7669. Min Act: -0.1700
Data Index: 1161585 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.7669. Min Act: -0.1700
Data Index: 3975231 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.7356. Min Act: -0.1700
Data Index: 4479603 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.7356. Min Act: -0.1700
Data Index: 3002296 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.7044. Min Act: -0.1700
Data Index: 7400467 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.7044. Min Act: -0.1700
Data Index: 269999 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.6731. Min Act: -0.1700
Data Index: 2682280 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.6731. Min Act: -0.1700
Data Index: 6304440 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.6731. Min Act: -0.1700
Data Index: 61944 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.6731. Min Act: -0.1700
Data Index: 1882891 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.7044. Min Act: -0.1700
Data Index: 1752986 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.6731. Min Act: -0.1700
Data Index: 3834398 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.6106. Min Act: -0.1700
Data Index: 1883897 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.6419. Min Act: -0.1700
Data Index: 8347350 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.6419. Min Act: -0.1700
Data Index: 4754202 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.6419. Min Act: -0.1700
Data Index: 4367131 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.6106. Min Act: -0.1700
Data Index: 7552325 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8606. Min Range: -5.8606
Max Act: 5.6106. Min Act: -0.1700
Data Index: 2151429 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19