Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4895 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.3202. Min Act: -0.1700
Data Index: 6753192 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.2264. Min Act: -0.1700
Data Index: 6350782 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.1014. Min Act: -0.1700
Data Index: 4366762 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.0077. Min Act: -0.1700
Data Index: 2689331 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.0077. Min Act: -0.1700
Data Index: 1424272 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3202. Min Range: -5.3202
Max Act: 5.0077. Min Act: -0.1700
Data Index: 8155837 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.9452. Min Act: -0.1700
Data Index: 8257162 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.9452. Min Act: -0.1700
Data Index: 5338302 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.9452. Min Act: -0.1700
Data Index: 4478971 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.9139. Min Act: -0.1700
Data Index: 793691 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.9139. Min Act: -0.1700
Data Index: 7801020 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.9139. Min Act: -0.1700
Data Index: 4568525 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.8827. Min Act: -0.1700
Data Index: 6520422 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.9139. Min Act: -0.1700
Data Index: 6550218 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.8514. Min Act: -0.1700
Data Index: 4670762 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.8202. Min Act: -0.1700
Data Index: 7395036 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.8202. Min Act: -0.1700
Data Index: 2645788 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.8514. Min Act: -0.1700
Data Index: 3016357 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.8202. Min Act: -0.1700
Data Index: 5258419 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3202. Min Range: -5.3202
Max Act: 4.8202. Min Act: -0.1700
Data Index: 6855868 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19