Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4414 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.9462. Min Act: -0.1700
Data Index: 7684024 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.8524. Min Act: -0.1700
Data Index: 6028495 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.7899. Min Act: -0.1700
Data Index: 7514362 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.7587. Min Act: -0.1700
Data Index: 2862694 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.7274. Min Act: -0.1700
Data Index: 6201435 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.6962. Min Act: -0.1700
Data Index: 968680 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.6649. Min Act: -0.1700
Data Index: 2626131 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.6649. Min Act: -0.1700
Data Index: 203581 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.6649. Min Act: -0.1700
Data Index: 5332191 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.6649. Min Act: -0.1700
Data Index: 5944939 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.6024. Min Act: -0.1700
Data Index: 2061257 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.6337. Min Act: -0.1700
Data Index: 181946 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.6337. Min Act: -0.1700
Data Index: 7424362 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.6024. Min Act: -0.1700
Data Index: 5476756 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.5712. Min Act: -0.1700
Data Index: 3146891 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.6024. Min Act: -0.1700
Data Index: 7968776 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.6024. Min Act: -0.1700
Data Index: 2082631 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.6337. Min Act: -0.1700
Data Index: 7684025 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.5712. Min Act: -0.1700
Data Index: 4128197 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9462. Min Range: -5.9462
Max Act: 5.5712. Min Act: -0.1700
Data Index: 2999011 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19