Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0058. Min Range: -4.0058
Max Act: 4.0058. Min Act: -0.1700
Data Index: 6522418 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.7557. Min Act: -0.1700
Data Index: 1067320 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.6462. Min Act: -0.1700
Data Index: 6716383 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.6149. Min Act: -0.1700
Data Index: 2871382 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.5836. Min Act: -0.1700
Data Index: 3572277 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.4896. Min Act: -0.1700
Data Index: 6645967 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.4739. Min Act: -0.1700
Data Index: 7972269 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.4113. Min Act: -0.1700
Data Index: 1917472 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.3642. Min Act: -0.1700
Data Index: 668355 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.3485. Min Act: -0.1700
Data Index: 1917471 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.3485. Min Act: -0.1700
Data Index: 7477099 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.3014. Min Act: -0.1700
Data Index: 5588082 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.3171. Min Act: -0.1700
Data Index: 4135593 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.3485. Min Act: -0.1700
Data Index: 5503391 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.3171. Min Act: -0.1700
Data Index: 1518140 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.3014. Min Act: -0.1700
Data Index: 1391034 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.2857. Min Act: -0.1700
Data Index: 4943258 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.2543. Min Act: -0.1700
Data Index: 1634019 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.2229. Min Act: -0.1700
Data Index: 4296222 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0058. Min Range: -4.0058
Max Act: 3.2386. Min Act: -0.1700
Data Index: 2031199 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19