Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6082 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2676. Min Range: -6.2676
Max Act: 6.2676. Min Act: -0.1700
Data Index: 1126638 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2676. Min Range: -6.2676
Max Act: 6.0489. Min Act: -0.1700
Data Index: 8516874 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2676. Min Range: -6.2676
Max Act: 6.0489. Min Act: -0.1700
Data Index: 2500973 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2676. Min Range: -6.2676
Max Act: 6.0489. Min Act: -0.1700
Data Index: 2415042 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2676. Min Range: -6.2676
Max Act: 6.0176. Min Act: -0.1700
Data Index: 2273653 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.9864. Min Act: -0.1700
Data Index: 5897333 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.9864. Min Act: -0.1700
Data Index: 5580623 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.9864. Min Act: -0.1700
Data Index: 1354592 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2676. Min Range: -6.2676
Max Act: 6.0176. Min Act: -0.1700
Data Index: 6027046 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.9864. Min Act: -0.1700
Data Index: 4127256 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.9551. Min Act: -0.1700
Data Index: 3588154 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.9551. Min Act: -0.1700
Data Index: 994952 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.9864. Min Act: -0.1700
Data Index: 469309 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.9239. Min Act: -0.1700
Data Index: 1331281 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.9239. Min Act: -0.1700
Data Index: 8782792 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.9239. Min Act: -0.1700
Data Index: 7057585 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.9239. Min Act: -0.1700
Data Index: 2341827 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.8926. Min Act: -0.1700
Data Index: 1537929 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.8926. Min Act: -0.1700
Data Index: 3873308 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2676. Min Range: -6.2676
Max Act: 5.8926. Min Act: -0.1700
Data Index: 3988536 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19