Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4632 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.4002. Min Act: -0.1700
Data Index: 2273041 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.4002. Min Act: -0.1700
Data Index: 2348042 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.3377. Min Act: -0.1700
Data Index: 6019130 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.3377. Min Act: -0.1700
Data Index: 6842886 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.3377. Min Act: -0.1700
Data Index: 2354889 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.2440. Min Act: -0.1700
Data Index: 5459653 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.2127. Min Act: -0.1700
Data Index: 7952238 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.2127. Min Act: -0.1700
Data Index: 32549 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.0877. Min Act: -0.1700
Data Index: 4510246 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.0564. Min Act: -0.1700
Data Index: 1342840 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.0564. Min Act: -0.1700
Data Index: 4696808 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.0564. Min Act: -0.1700
Data Index: 3863649 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.0564. Min Act: -0.1700
Data Index: 739156 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.0564. Min Act: -0.1700
Data Index: 5189248 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.0252. Min Act: -0.1700
Data Index: 8792623 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.0252. Min Act: -0.1700
Data Index: 5733257 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.0252. Min Act: -0.1700
Data Index: 8414470 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.0252. Min Act: -0.1700
Data Index: 4676793 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4002. Min Range: -4.4002
Max Act: 4.0252. Min Act: -0.1700
Data Index: 5550731 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4002. Min Range: -4.4002
Max Act: 3.9627. Min Act: -0.1700
Data Index: 3351760 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19