Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4246 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.9912. Min Act: -0.1700
Data Index: 1141720 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.9599. Min Act: -0.1700
Data Index: 8399729 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.8349. Min Act: -0.1700
Data Index: 6119694 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.7724. Min Act: -0.1700
Data Index: 8051575 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.7412. Min Act: -0.1700
Data Index: 7461915 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.8037. Min Act: -0.1700
Data Index: 4098088 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.7724. Min Act: -0.1700
Data Index: 4067054 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.8037. Min Act: -0.1700
Data Index: 8568618 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.6787. Min Act: -0.1700
Data Index: 6115778 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.6787. Min Act: -0.1700
Data Index: 1554714 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.6474. Min Act: -0.1700
Data Index: 6486413 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.6474. Min Act: -0.1700
Data Index: 3112180 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.6162. Min Act: -0.1700
Data Index: 3065806 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.5849. Min Act: -0.1700
Data Index: 764456 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.6162. Min Act: -0.1700
Data Index: 744032 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.5537. Min Act: -0.1700
Data Index: 3244306 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.6162. Min Act: -0.1700
Data Index: 1687346 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.5849. Min Act: -0.1700
Data Index: 6112399 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.5849. Min Act: -0.1700
Data Index: 3180317 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9912. Min Range: -5.9912
Max Act: 5.5537. Min Act: -0.1700
Data Index: 8126248 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19