Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 501 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.5444. Min Act: -0.1700
Data Index: 4813552 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.5444. Min Act: -0.1700
Data Index: 6684500 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.5131. Min Act: -0.1700
Data Index: 7738483 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.5131. Min Act: -0.1699
Data Index: 5246295 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.5131. Min Act: -0.1700
Data Index: 2645487 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4819. Min Act: -0.1700
Data Index: 3611310 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4819. Min Act: -0.1700
Data Index: 2982390 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4506. Min Act: -0.1700
Data Index: 283549 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4506. Min Act: -0.1700
Data Index: 2201069 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4194. Min Act: -0.1700
Data Index: 2645488 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4506. Min Act: -0.1700
Data Index: 5131347 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4506. Min Act: -0.1699
Data Index: 6631012 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4819. Min Act: -0.1700
Data Index: 611566 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4819. Min Act: -0.1700
Data Index: 1685288 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4506. Min Act: -0.1700
Data Index: 3774221 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4194. Min Act: -0.1700
Data Index: 4524614 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4194. Min Act: -0.1700
Data Index: 416758 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4506. Min Act: -0.1700
Data Index: 4474786 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4194. Min Act: -0.1700
Data Index: 4138412 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.4194. Min Act: -0.1700
Data Index: 7035520 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19