Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4123 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1555. Min Range: -5.1555
Max Act: 5.1555. Min Act: -0.1700
Data Index: 339577 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1555. Min Range: -5.1555
Max Act: 5.0305. Min Act: -0.1700
Data Index: 7217638 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1555. Min Range: -5.1555
Max Act: 5.0305. Min Act: -0.1700
Data Index: 7959321 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1555. Min Range: -5.1555
Max Act: 5.0305. Min Act: -0.1700
Data Index: 8352756 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9993. Min Act: -0.1700
Data Index: 3041389 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9993. Min Act: -0.1700
Data Index: 3279746 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9680. Min Act: -0.1700
Data Index: 8424558 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9680. Min Act: -0.1700
Data Index: 604353 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9680. Min Act: -0.1700
Data Index: 7393961 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9680. Min Act: -0.1700
Data Index: 3753063 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9680. Min Act: -0.1700
Data Index: 6480308 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9368. Min Act: -0.1700
Data Index: 893167 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9680. Min Act: -0.1700
Data Index: 8227336 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9680. Min Act: -0.1700
Data Index: 7911169 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9680. Min Act: -0.1700
Data Index: 5283268 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9368. Min Act: -0.1700
Data Index: 2648905 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9680. Min Act: -0.1700
Data Index: 5734351 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9368. Min Act: -0.1700
Data Index: 3455642 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.9368. Min Act: -0.1700
Data Index: 2805032 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1555. Min Range: -5.1555
Max Act: 4.8743. Min Act: -0.1700
Data Index: 309869 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19