Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4355 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.3538. Min Act: -0.1700
Data Index: 3500306 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.2913. Min Act: -0.1700
Data Index: 1897245 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.1976. Min Act: -0.1700
Data Index: 8237528 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.1351. Min Act: -0.1700
Data Index: 1212422 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.1663. Min Act: -0.1700
Data Index: 664926 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.0726. Min Act: -0.1700
Data Index: 1735319 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.0413. Min Act: -0.1700
Data Index: 7074830 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.0413. Min Act: -0.1700
Data Index: 6421713 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.0413. Min Act: -0.1700
Data Index: 8383032 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.0413. Min Act: -0.1700
Data Index: 1373406 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.0101. Min Act: -0.1700
Data Index: 715664 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.0101. Min Act: -0.1700
Data Index: 6758672 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.0101. Min Act: -0.1700
Data Index: 231134 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3538. Min Range: -5.3538
Max Act: 5.0101. Min Act: -0.1700
Data Index: 520311 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3538. Min Range: -5.3538
Max Act: 4.9788. Min Act: -0.1700
Data Index: 4130534 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3538. Min Range: -5.3538
Max Act: 4.9788. Min Act: -0.1700
Data Index: 5993639 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3538. Min Range: -5.3538
Max Act: 4.9476. Min Act: -0.1700
Data Index: 592351 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3538. Min Range: -5.3538
Max Act: 4.9476. Min Act: -0.1700
Data Index: 4929495 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3538. Min Range: -5.3538
Max Act: 4.9476. Min Act: -0.1700
Data Index: 4986047 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3538. Min Range: -5.3538
Max Act: 4.9476. Min Act: -0.1700
Data Index: 567528 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19