Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2593 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.6723. Min Act: -0.1700
Data Index: 3804523 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.6098. Min Act: -0.1700
Data Index: 1989634 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.6098. Min Act: -0.1700
Data Index: 4506346 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.5473. Min Act: -0.1700
Data Index: 8555618 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.4848. Min Act: -0.1700
Data Index: 427829 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.4848. Min Act: -0.1700
Data Index: 5549174 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.4223. Min Act: -0.1700
Data Index: 3101807 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.3910. Min Act: -0.1700
Data Index: 7672673 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.3910. Min Act: -0.1700
Data Index: 858766 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.3598. Min Act: -0.1700
Data Index: 6821243 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.3598. Min Act: -0.1700
Data Index: 5227678 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.2973. Min Act: -0.1700
Data Index: 2255289 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.3598. Min Act: -0.1700
Data Index: 5882415 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.3285. Min Act: -0.1700
Data Index: 4278692 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.2973. Min Act: -0.1700
Data Index: 5376454 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.2660. Min Act: -0.1700
Data Index: 5526828 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.2660. Min Act: -0.1700
Data Index: 2290433 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.2660. Min Act: -0.1700
Data Index: 8257366 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.2660. Min Act: -0.1700
Data Index: 7880428 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6723. Min Range: -7.6723
Max Act: 7.2348. Min Act: -0.1700
Data Index: 4506462 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19