Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.7033. Min Act: -0.1700
Data Index: 8642136 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.4845. Min Act: -0.1700
Data Index: 4747679 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.4845. Min Act: -0.1700
Data Index: 2895832 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.3595. Min Act: -0.1700
Data Index: 676843 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.3595. Min Act: -0.1700
Data Index: 4141817 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.3595. Min Act: -0.1700
Data Index: 6119369 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.3595. Min Act: -0.1700
Data Index: 5112368 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.2970. Min Act: -0.1700
Data Index: 3349466 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.2345. Min Act: -0.1700
Data Index: 896311 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.2345. Min Act: -0.1700
Data Index: 1249199 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.2345. Min Act: -0.1700
Data Index: 7040757 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.2345. Min Act: -0.1700
Data Index: 217155 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.2345. Min Act: -0.1700
Data Index: 3583075 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.2033. Min Act: -0.1700
Data Index: 8065648 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.1720. Min Act: -0.1700
Data Index: 6099024 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.1720. Min Act: -0.1700
Data Index: 5704716 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.1720. Min Act: -0.1700
Data Index: 2444613 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.1720. Min Act: -0.1700
Data Index: 4728582 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.1720. Min Act: -0.1700
Data Index: 3336160 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7033. Min Range: -5.7033
Max Act: 5.1720. Min Act: -0.1700
Data Index: 1670028 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19