Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2305 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4531. Min Range: -5.4531
Max Act: 5.4531. Min Act: -0.1700
Data Index: 2253505 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.9218. Min Act: -0.1700
Data Index: 5214202 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.8593. Min Act: -0.1700
Data Index: 7138781 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.8281. Min Act: -0.1700
Data Index: 7611959 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.7656. Min Act: -0.1700
Data Index: 344979 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.7656. Min Act: -0.1700
Data Index: 6609512 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.7656. Min Act: -0.1700
Data Index: 8062321 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.7031. Min Act: -0.1700
Data Index: 4499026 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.6718. Min Act: -0.1700
Data Index: 1727910 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.7031. Min Act: -0.1700
Data Index: 5111432 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.6406. Min Act: -0.1700
Data Index: 7409943 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.6406. Min Act: -0.1700
Data Index: 7616191 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.6406. Min Act: -0.1700
Data Index: 8041919 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.6406. Min Act: -0.1700
Data Index: 7088083 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.6406. Min Act: -0.1700
Data Index: 254699 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.6093. Min Act: -0.1700
Data Index: 3026675 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.6093. Min Act: -0.1700
Data Index: 2097124 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.6093. Min Act: -0.1700
Data Index: 7058699 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.5781. Min Act: -0.1700
Data Index: 5615222 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4531. Min Range: -5.4531
Max Act: 4.5781. Min Act: -0.1700
Data Index: 1413103 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19