Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.4069. Min Act: -0.1700
Data Index: 3364963 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.2819. Min Act: -0.1700
Data Index: 4709435 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.2506. Min Act: -0.1700
Data Index: 3933484 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.2194. Min Act: -0.1700
Data Index: 309292 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.2194. Min Act: -0.1700
Data Index: 3156130 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.2194. Min Act: -0.1700
Data Index: 6370233 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.2194. Min Act: -0.1700
Data Index: 416473 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.2194. Min Act: -0.1700
Data Index: 4831580 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.1881. Min Act: -0.1700
Data Index: 3933491 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.1569. Min Act: -0.1700
Data Index: 4280605 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.1256. Min Act: -0.1700
Data Index: 7398927 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.1256. Min Act: -0.1700
Data Index: 42591 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.1256. Min Act: -0.1700
Data Index: 4476086 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.0944. Min Act: -0.1700
Data Index: 5823863 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.0944. Min Act: -0.1700
Data Index: 467640 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.0944. Min Act: -0.1700
Data Index: 1027644 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.0944. Min Act: -0.1700
Data Index: 346064 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.0631. Min Act: -0.1700
Data Index: 5937346 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.0944. Min Act: -0.1700
Data Index: 3426129 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4069. Min Range: -4.4069
Max Act: 4.1256. Min Act: -0.1700
Data Index: 3967553 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19