Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4961. Min Range: -9.4961
Max Act: 9.4961. Min Act: -0.1700
Data Index: 2498964 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4961. Min Range: -9.4961
Max Act: 9.3711. Min Act: -0.1700
Data Index: 5659649 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4961. Min Range: -9.4961
Max Act: 9.3711. Min Act: -0.1700
Data Index: 7609631 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4961. Min Range: -9.4961
Max Act: 9.3086. Min Act: -0.1700
Data Index: 1746073 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4961. Min Range: -9.4961
Max Act: 9.1836. Min Act: -0.1700
Data Index: 7086983 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4961. Min Range: -9.4961
Max Act: 9.0586. Min Act: -0.1700
Data Index: 4243107 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.9961. Min Act: -0.1700
Data Index: 1482048 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.9961. Min Act: -0.1700
Data Index: 2474172 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.9961. Min Act: -0.1700
Data Index: 154981 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.9336. Min Act: -0.1700
Data Index: 3455737 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.9336. Min Act: -0.1700
Data Index: 8343509 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.9336. Min Act: -0.1700
Data Index: 2143984 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.8086. Min Act: -0.1700
Data Index: 7713634 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.8086. Min Act: -0.1700
Data Index: 366345 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.8086. Min Act: -0.1700
Data Index: 8589263 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.7461. Min Act: -0.1700
Data Index: 81833 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.7461. Min Act: -0.1700
Data Index: 6868340 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.7461. Min Act: -0.1700
Data Index: 8377554 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.7461. Min Act: -0.1700
Data Index: 2347770 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4961. Min Range: -9.4961
Max Act: 8.8086. Min Act: -0.1700
Data Index: 1448285 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19