Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0825. Min Range: -6.0825
Max Act: 6.0825. Min Act: -0.1700
Data Index: 5702774 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.8950. Min Act: -0.1700
Data Index: 3368547 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.9263. Min Act: -0.1700
Data Index: 4353555 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.8950. Min Act: -0.1700
Data Index: 2556035 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.8325. Min Act: -0.1700
Data Index: 4203859 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.8325. Min Act: -0.1700
Data Index: 5954234 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.8638. Min Act: -0.1700
Data Index: 6295881 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.8013. Min Act: -0.1700
Data Index: 2473073 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.8013. Min Act: -0.1700
Data Index: 1119501 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.7700. Min Act: -0.1700
Data Index: 4283563 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.7700. Min Act: -0.1700
Data Index: 5272623 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.7700. Min Act: -0.1700
Data Index: 2634714 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.7388. Min Act: -0.1700
Data Index: 2086424 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.7700. Min Act: -0.1700
Data Index: 1411286 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.7388. Min Act: -0.1700
Data Index: 173484 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.7075. Min Act: -0.1700
Data Index: 6779996 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.7075. Min Act: -0.1700
Data Index: 4575202 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.7075. Min Act: -0.1700
Data Index: 1061633 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.7075. Min Act: -0.1700
Data Index: 788604 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0825. Min Range: -6.0825
Max Act: 5.7075. Min Act: -0.1700
Data Index: 3447180 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19