Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4999 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0792. Min Range: -5.0792
Max Act: 5.0792. Min Act: -0.1700
Data Index: 5128766 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0792. Min Range: -5.0792
Max Act: 5.0480. Min Act: -0.1700
Data Index: 4121237 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0792. Min Range: -5.0792
Max Act: 5.0167. Min Act: -0.1700
Data Index: 74904 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0792. Min Range: -5.0792
Max Act: 5.0167. Min Act: -0.1700
Data Index: 4480100 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0792. Min Range: -5.0792
Max Act: 5.0167. Min Act: -0.1700
Data Index: 7239870 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.9542. Min Act: -0.1700
Data Index: 1292170 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.9855. Min Act: -0.1700
Data Index: 2615050 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.9230. Min Act: -0.1700
Data Index: 8649000 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.8917. Min Act: -0.1700
Data Index: 1062132 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.9230. Min Act: -0.1700
Data Index: 4486633 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.8917. Min Act: -0.1700
Data Index: 2401828 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.8917. Min Act: -0.1700
Data Index: 3539791 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.8917. Min Act: -0.1700
Data Index: 8298906 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.8917. Min Act: -0.1700
Data Index: 1770177 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.8917. Min Act: -0.1700
Data Index: 6540993 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.8917. Min Act: -0.1700
Data Index: 6183861 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.8917. Min Act: -0.1700
Data Index: 1187172 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.8917. Min Act: -0.1700
Data Index: 5154163 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.8917. Min Act: -0.1700
Data Index: 4839902 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0792. Min Range: -5.0792
Max Act: 4.8605. Min Act: -0.1700
Data Index: 4966679 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19