Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5526 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.3944. Min Act: -0.1700
Data Index: 2018568 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.3631. Min Act: -0.1700
Data Index: 2797499 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.3474. Min Act: -0.1700
Data Index: 5502879 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.3317. Min Act: -0.1700
Data Index: 1128856 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.3003. Min Act: -0.1700
Data Index: 2503096 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.2846. Min Act: -0.1700
Data Index: 4530418 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.2217. Min Act: -0.1700
Data Index: 2996930 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.2060. Min Act: -0.1700
Data Index: 6645910 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.2060. Min Act: -0.1700
Data Index: 1294295 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.2217. Min Act: -0.1700
Data Index: 4482567 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.2060. Min Act: -0.1700
Data Index: 4745093 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.2217. Min Act: -0.1700
Data Index: 4530419 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.2060. Min Act: -0.1700
Data Index: 1488477 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.2060. Min Act: -0.1700
Data Index: 1194198 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.1903. Min Act: -0.1700
Data Index: 5107003 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.1903. Min Act: -0.1700
Data Index: 4799284 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.1903. Min Act: -0.1700
Data Index: 5204790 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.1903. Min Act: -0.1700
Data Index: 6047549 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.1903. Min Act: -0.1700
Data Index: 1593238 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3944. Min Range: -3.3944
Max Act: 3.1903. Min Act: -0.1700
Data Index: 3025211 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19