Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2187 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3132. Min Range: -7.3132
Max Act: 7.3132. Min Act: -0.1700
Data Index: 4094797 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3132. Min Range: -7.3132
Max Act: 7.2507. Min Act: -0.1700
Data Index: 8202647 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3132. Min Range: -7.3132
Max Act: 7.1882. Min Act: -0.1700
Data Index: 6176590 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3132. Min Range: -7.3132
Max Act: 7.1257. Min Act: -0.1700
Data Index: 1569755 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3132. Min Range: -7.3132
Max Act: 7.1569. Min Act: -0.1700
Data Index: 3684440 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3132. Min Range: -7.3132
Max Act: 7.1257. Min Act: -0.1700
Data Index: 5890922 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3132. Min Range: -7.3132
Max Act: 6.9694. Min Act: -0.1700
Data Index: 452125 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3132. Min Range: -7.3132
Max Act: 7.0007. Min Act: -0.1700
Data Index: 8138649 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3132. Min Range: -7.3132
Max Act: 6.9382. Min Act: -0.1700
Data Index: 955916 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3132. Min Range: -7.3132
Max Act: 6.9069. Min Act: -0.1700
Data Index: 6304365 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3132. Min Range: -7.3132
Max Act: 6.8444. Min Act: -0.1700
Data Index: 2890099 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3132. Min Range: -7.3132
Max Act: 6.8444. Min Act: -0.1700
Data Index: 494677 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3132. Min Range: -7.3132
Max Act: 6.8757. Min Act: -0.1700
Data Index: 42647 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3132. Min Range: -7.3132
Max Act: 6.8132. Min Act: -0.1700
Data Index: 7795176 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3132. Min Range: -7.3132
Max Act: 6.7819. Min Act: -0.1700
Data Index: 2102938 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3132. Min Range: -7.3132
Max Act: 6.7507. Min Act: -0.1700
Data Index: 640924 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3132. Min Range: -7.3132
Max Act: 6.7507. Min Act: -0.1700
Data Index: 6883019 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3132. Min Range: -7.3132
Max Act: 6.7194. Min Act: -0.1700
Data Index: 3726136 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3132. Min Range: -7.3132
Max Act: 6.7194. Min Act: -0.1700
Data Index: 3417690 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3132. Min Range: -7.3132
Max Act: 6.7507. Min Act: -0.1700
Data Index: 83395 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19