Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6359 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1573. Min Range: -8.1573
Max Act: 8.1573. Min Act: -0.1700
Data Index: 7081116 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1573. Min Range: -8.1573
Max Act: 8.1573. Min Act: -0.1700
Data Index: 7724790 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.7823. Min Act: -0.1700
Data Index: 3761585 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.7823. Min Act: -0.1700
Data Index: 3199045 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.7198. Min Act: -0.1700
Data Index: 6347492 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.6573. Min Act: -0.1700
Data Index: 8608457 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.6573. Min Act: -0.1700
Data Index: 3920110 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.6573. Min Act: -0.1700
Data Index: 7197781 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.5010. Min Act: -0.1700
Data Index: 5014390 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.4698. Min Act: -0.1700
Data Index: 8821459 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.4698. Min Act: -0.1700
Data Index: 7663919 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.5010. Min Act: -0.1700
Data Index: 3122875 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.4385. Min Act: -0.1700
Data Index: 4948725 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.4385. Min Act: -0.1700
Data Index: 6598132 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.4385. Min Act: -0.1700
Data Index: 1521822 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.3448. Min Act: -0.1700
Data Index: 3159198 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.3760. Min Act: -0.1700
Data Index: 1247462 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.3448. Min Act: -0.1700
Data Index: 7160165 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.3135. Min Act: -0.1700
Data Index: 3264001 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1573. Min Range: -8.1573
Max Act: 7.3135. Min Act: -0.1700
Data Index: 775433 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19