Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2272 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1672. Min Range: -3.1672
Max Act: 3.1672. Min Act: -0.1700
Data Index: 6014219 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1672. Min Range: -3.1672
Max Act: 3.0885. Min Act: -0.1700
Data Index: 3758854 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1672. Min Range: -3.1672
Max Act: 3.0885. Min Act: -0.1700
Data Index: 3150051 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1672. Min Range: -3.1672
Max Act: 3.0727. Min Act: -0.1700
Data Index: 5629270 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1672. Min Range: -3.1672
Max Act: 3.0727. Min Act: -0.1700
Data Index: 6014220 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1672. Min Range: -3.1672
Max Act: 3.0411. Min Act: -0.1700
Data Index: 7728619 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1672. Min Range: -3.1672
Max Act: 3.0254. Min Act: -0.1700
Data Index: 3851232 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1672. Min Range: -3.1672
Max Act: 3.0411. Min Act: -0.1700
Data Index: 6606605 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1672. Min Range: -3.1672
Max Act: 3.0254. Min Act: -0.1700
Data Index: 4380816 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1672. Min Range: -3.1672
Max Act: 3.0096. Min Act: -0.1700
Data Index: 7583165 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1672. Min Range: -3.1672
Max Act: 3.0096. Min Act: -0.1700
Data Index: 5808345 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1672. Min Range: -3.1672
Max Act: 3.0096. Min Act: -0.1700
Data Index: 4601027 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1672. Min Range: -3.1672
Max Act: 2.9779. Min Act: -0.1700
Data Index: 4485841 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1672. Min Range: -3.1672
Max Act: 2.9779. Min Act: -0.1700
Data Index: 8783475 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1672. Min Range: -3.1672
Max Act: 2.9779. Min Act: -0.1700
Data Index: 5486696 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1672. Min Range: -3.1672
Max Act: 2.9779. Min Act: -0.1700
Data Index: 6962953 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1672. Min Range: -3.1672
Max Act: 2.9621. Min Act: -0.1700
Data Index: 1186502 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1672. Min Range: -3.1672
Max Act: 2.9621. Min Act: -0.1700
Data Index: 8372996 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1672. Min Range: -3.1672
Max Act: 2.9621. Min Act: -0.1700
Data Index: 1244347 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1672. Min Range: -3.1672
Max Act: 2.9463. Min Act: -0.1700
Data Index: 2554966 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19