Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2350 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.6676. Min Act: -0.1700
Data Index: 4805426 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.6051. Min Act: -0.1700
Data Index: 7174023 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.5426. Min Act: -0.1700
Data Index: 3284837 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.5426. Min Act: -0.1700
Data Index: 8067157 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.4801. Min Act: -0.1700
Data Index: 1383191 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.4176. Min Act: -0.1700
Data Index: 8169814 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.3551. Min Act: -0.1700
Data Index: 4396349 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.3551. Min Act: -0.1700
Data Index: 5724718 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.2926. Min Act: -0.1700
Data Index: 7025652 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.1676. Min Act: -0.1700
Data Index: 5809056 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.2301. Min Act: -0.1700
Data Index: 6567275 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.1051. Min Act: -0.1700
Data Index: 4864210 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.2301. Min Act: -0.1700
Data Index: 2578239 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.1676. Min Act: -0.1700
Data Index: 7848693 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.1051. Min Act: -0.1700
Data Index: 6736992 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.0738. Min Act: -0.1700
Data Index: 327295 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.0426. Min Act: -0.1700
Data Index: 2298605 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.0113. Min Act: -0.1700
Data Index: 5289196 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.0113. Min Act: -0.1700
Data Index: 6559356 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6676. Min Range: -8.6676
Max Act: 8.0113. Min Act: -0.1700
Data Index: 7562913 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19