Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3194 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.4723. Min Act: -0.1700
Data Index: 803573 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.4410. Min Act: -0.1700
Data Index: 4942512 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.4096. Min Act: -0.1700
Data Index: 1378345 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.4096. Min Act: -0.1700
Data Index: 6614032 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.4096. Min Act: -0.1700
Data Index: 3042841 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3783. Min Act: -0.1700
Data Index: 1889745 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3783. Min Act: -0.1700
Data Index: 3774658 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3783. Min Act: -0.1700
Data Index: 5236463 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3783. Min Act: -0.1700
Data Index: 6701874 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3783. Min Act: -0.1700
Data Index: 7814175 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3783. Min Act: -0.1700
Data Index: 3389912 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3783. Min Act: -0.1700
Data Index: 976786 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3469. Min Act: -0.1700
Data Index: 1321240 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3469. Min Act: -0.1700
Data Index: 3081848 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3469. Min Act: -0.1700
Data Index: 113635 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3469. Min Act: -0.1700
Data Index: 699815 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3469. Min Act: -0.1700
Data Index: 1662956 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3469. Min Act: -0.1700
Data Index: 1025560 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3469. Min Act: -0.1700
Data Index: 295289 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4723. Min Range: -3.4723
Max Act: 3.3469. Min Act: -0.1700
Data Index: 951553 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19