Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4963 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2229. Min Range: -11.2229
Max Act: 11.2229. Min Act: -0.1700
Data Index: 7447064 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.5354. Min Act: -0.1700
Data Index: 4943871 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.2854. Min Act: -0.1700
Data Index: 7979417 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.2854. Min Act: -0.1700
Data Index: 6595932 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.2854. Min Act: -0.1700
Data Index: 6922384 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.2229. Min Act: -0.1700
Data Index: 2085906 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.2229. Min Act: -0.1700
Data Index: 8664972 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.2229. Min Act: -0.1700
Data Index: 2773481 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.1604. Min Act: -0.1700
Data Index: 7117492 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.2229. Min Act: -0.1700
Data Index: 2957547 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.1604. Min Act: -0.1700
Data Index: 8743704 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.1604. Min Act: -0.1700
Data Index: 3356297 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.1604. Min Act: -0.1700
Data Index: 4371263 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.0979. Min Act: -0.1700
Data Index: 1717751 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.0979. Min Act: -0.1700
Data Index: 8592053 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.0979. Min Act: -0.1700
Data Index: 3392606 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.0979. Min Act: -0.1700
Data Index: 2460703 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.0354. Min Act: -0.1700
Data Index: 8400755 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2229. Min Range: -11.2229
Max Act: 9.9729. Min Act: -0.1700
Data Index: 4276486 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2229. Min Range: -11.2229
Max Act: 10.0354. Min Act: -0.1700
Data Index: 2536398 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19