Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3835 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.8786. Min Act: -0.1700
Data Index: 6970689 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.8161. Min Act: -0.1700
Data Index: 6485799 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.7066. Min Act: -0.1700
Data Index: 635079 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.6753. Min Act: -0.1700
Data Index: 4485622 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.6440. Min Act: -0.1700
Data Index: 4498970 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.6597. Min Act: -0.1700
Data Index: 6290124 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.6284. Min Act: -0.1700
Data Index: 5986870 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.6440. Min Act: -0.1700
Data Index: 4934173 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.6127. Min Act: -0.1700
Data Index: 5185585 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.6284. Min Act: -0.1700
Data Index: 1305705 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.6127. Min Act: -0.1700
Data Index: 146776 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.5971. Min Act: -0.1700
Data Index: 7103428 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.5814. Min Act: -0.1700
Data Index: 1338130 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.5814. Min Act: -0.1700
Data Index: 3208848 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.5658. Min Act: -0.1700
Data Index: 6878887 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.5814. Min Act: -0.1700
Data Index: 3889676 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.5501. Min Act: -0.1700
Data Index: 8760890 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.5501. Min Act: -0.1700
Data Index: 4586345 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.5501. Min Act: -0.1700
Data Index: 7997939 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8786. Min Range: -3.8786
Max Act: 3.5501. Min Act: -0.1700
Data Index: 4291360 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19