Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1723. Min Range: -8.1723
Max Act: 8.1723. Min Act: -0.1700
Data Index: 7414171 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1723. Min Range: -8.1723
Max Act: 8.0473. Min Act: -0.1700
Data Index: 8026021 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.9848. Min Act: -0.1700
Data Index: 5453772 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.9223. Min Act: -0.1700
Data Index: 5243943 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.7973. Min Act: -0.1700
Data Index: 634009 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.7973. Min Act: -0.1700
Data Index: 1495494 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.7348. Min Act: -0.1700
Data Index: 3667246 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.6723. Min Act: -0.1700
Data Index: 5411817 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.6723. Min Act: -0.1700
Data Index: 2969766 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.6723. Min Act: -0.1700
Data Index: 7645219 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.6723. Min Act: -0.1700
Data Index: 1058325 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.6098. Min Act: -0.1700
Data Index: 7152431 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.5785. Min Act: -0.1700
Data Index: 488003 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.5473. Min Act: -0.1700
Data Index: 8144414 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.5473. Min Act: -0.1700
Data Index: 6272034 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.5473. Min Act: -0.1700
Data Index: 7857155 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.5473. Min Act: -0.1700
Data Index: 2727083 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.5160. Min Act: -0.1700
Data Index: 4731915 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.5160. Min Act: -0.1700
Data Index: 5275069 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1723. Min Range: -8.1723
Max Act: 7.5160. Min Act: -0.1700
Data Index: 1574998 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19