Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3191 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.8956. Min Act: -0.1700
Data Index: 6326451 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.8644. Min Act: -0.1700
Data Index: 4822474 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.8331. Min Act: -0.1700
Data Index: 6856576 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.8331. Min Act: -0.1700
Data Index: 4608316 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.7706. Min Act: -0.1700
Data Index: 3519378 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.7706. Min Act: -0.1700
Data Index: 8557922 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.7081. Min Act: -0.1700
Data Index: 6724625 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.7081. Min Act: -0.1700
Data Index: 25658 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.7081. Min Act: -0.1700
Data Index: 4932709 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.6769. Min Act: -0.1700
Data Index: 1019602 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.7081. Min Act: -0.1700
Data Index: 2035361 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.6456. Min Act: -0.1700
Data Index: 2366555 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.6456. Min Act: -0.1700
Data Index: 3925405 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.6144. Min Act: -0.1700
Data Index: 483579 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.6456. Min Act: -0.1700
Data Index: 6445554 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.6144. Min Act: -0.1700
Data Index: 6135824 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.6769. Min Act: -0.1700
Data Index: 5459680 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.6144. Min Act: -0.1700
Data Index: 2968912 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.6144. Min Act: -0.1700
Data Index: 5799992 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8956. Min Range: -4.8956
Max Act: 4.5831. Min Act: -0.1700
Data Index: 202475 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19