Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3776 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4499. Min Range: -7.4499
Max Act: 7.4499. Min Act: -0.1700
Data Index: 1602179 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4499. Min Range: -7.4499
Max Act: 7.3249. Min Act: -0.1700
Data Index: 642972 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4499. Min Range: -7.4499
Max Act: 7.2624. Min Act: -0.1700
Data Index: 6310613 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4499. Min Range: -7.4499
Max Act: 7.2312. Min Act: -0.1700
Data Index: 4974285 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4499. Min Range: -7.4499
Max Act: 7.1062. Min Act: -0.1700
Data Index: 5210506 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4499. Min Range: -7.4499
Max Act: 7.0749. Min Act: -0.1700
Data Index: 5444143 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4499. Min Range: -7.4499
Max Act: 7.0749. Min Act: -0.1700
Data Index: 2994926 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4499. Min Range: -7.4499
Max Act: 7.0124. Min Act: -0.1700
Data Index: 5585393 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4499. Min Range: -7.4499
Max Act: 6.9812. Min Act: -0.1700
Data Index: 2940367 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4499. Min Range: -7.4499
Max Act: 6.9812. Min Act: -0.1700
Data Index: 8242935 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4499. Min Range: -7.4499
Max Act: 7.0124. Min Act: -0.1700
Data Index: 8513212 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4499. Min Range: -7.4499
Max Act: 6.9812. Min Act: -0.1700
Data Index: 3708287 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4499. Min Range: -7.4499
Max Act: 6.9499. Min Act: -0.1700
Data Index: 5682171 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4499. Min Range: -7.4499
Max Act: 6.9499. Min Act: -0.1700
Data Index: 2533993 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4499. Min Range: -7.4499
Max Act: 6.9499. Min Act: -0.1700
Data Index: 4425250 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4499. Min Range: -7.4499
Max Act: 6.9499. Min Act: -0.1700
Data Index: 7274027 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4499. Min Range: -7.4499
Max Act: 6.9187. Min Act: -0.1700
Data Index: 61272 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4499. Min Range: -7.4499
Max Act: 6.8562. Min Act: -0.1700
Data Index: 2410713 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4499. Min Range: -7.4499
Max Act: 6.9187. Min Act: -0.1700
Data Index: 4635957 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4499. Min Range: -7.4499
Max Act: 6.8874. Min Act: -0.1700
Data Index: 2616106 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19