Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4521 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.8667. Min Act: -0.1700
Data Index: 248700 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.7729. Min Act: -0.1700
Data Index: 490104 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.7416. Min Act: -0.1700
Data Index: 6291579 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.6947. Min Act: -0.1700
Data Index: 5060064 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.6634. Min Act: -0.1700
Data Index: 5952163 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.6791. Min Act: -0.1700
Data Index: 5026428 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.6791. Min Act: -0.1700
Data Index: 5914239 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.6634. Min Act: -0.1700
Data Index: 3752459 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.6634. Min Act: -0.1700
Data Index: 768051 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.6478. Min Act: -0.1700
Data Index: 880975 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.6478. Min Act: -0.1700
Data Index: 7433428 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.6634. Min Act: -0.1700
Data Index: 7432803 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.6008. Min Act: -0.1700
Data Index: 1651501 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.6008. Min Act: -0.1700
Data Index: 6126937 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.6165. Min Act: -0.1700
Data Index: 7431625 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.6008. Min Act: -0.1700
Data Index: 3645108 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.5695. Min Act: -0.1700
Data Index: 6320391 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.5852. Min Act: -0.1700
Data Index: 5113288 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.5852. Min Act: -0.1700
Data Index: 6372384 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8667. Min Range: -3.8667
Max Act: 3.5852. Min Act: -0.1700
Data Index: 3182633 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19