Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2189 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.4762. Min Act: -0.1700
Data Index: 686330 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.4137. Min Act: -0.1695
Data Index: 6366578 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.4449. Min Act: -0.1700
Data Index: 3782756 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.4137. Min Act: -0.1700
Data Index: 553909 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.3512. Min Act: -0.1700
Data Index: 3980466 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.3199. Min Act: -0.1700
Data Index: 1142287 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.3199. Min Act: -0.1700
Data Index: 6145955 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.2574. Min Act: -0.1700
Data Index: 3336345 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.2262. Min Act: -0.1700
Data Index: 8444648 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.2262. Min Act: -0.1700
Data Index: 159953 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.2262. Min Act: -0.1700
Data Index: 8444658 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.2262. Min Act: -0.1700
Data Index: 7215674 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.2262. Min Act: -0.1699
Data Index: 3397402 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.1949. Min Act: -0.1700
Data Index: 6143362 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.1949. Min Act: -0.1700
Data Index: 5036204 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.1637. Min Act: -0.1699
Data Index: 4479455 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.1949. Min Act: -0.1700
Data Index: 464860 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.1949. Min Act: -0.1700
Data Index: 2216217 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.1949. Min Act: -0.1700
Data Index: 234920 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4762. Min Range: -5.4762
Max Act: 5.1949. Min Act: -0.1700
Data Index: 5005683 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19