Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4988 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.2389. Min Act: -0.1700
Data Index: 1877976 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.1917. Min Act: -0.1700
Data Index: 1877979 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.1602. Min Act: -0.1700
Data Index: 791726 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.1602. Min Act: -0.1700
Data Index: 1877978 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.1288. Min Act: -0.1700
Data Index: 8713182 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0972. Min Act: -0.1700
Data Index: 1877975 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0657. Min Act: -0.1700
Data Index: 6418015 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0815. Min Act: -0.1700
Data Index: 7898935 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0657. Min Act: -0.1700
Data Index: 1802391 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0657. Min Act: -0.1700
Data Index: 4782383 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0657. Min Act: -0.1700
Data Index: 8264079 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0341. Min Act: -0.1700
Data Index: 7767692 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0499. Min Act: -0.1700
Data Index: 6736269 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0341. Min Act: -0.1700
Data Index: 8172795 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0184. Min Act: -0.1700
Data Index: 3015885 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0184. Min Act: -0.1700
Data Index: 2139776 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2389. Min Range: -3.2389
Max Act: 2.9867. Min Act: -0.1700
Data Index: 8527652 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0026. Min Act: -0.1700
Data Index: 4237163 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0026. Min Act: -0.1700
Data Index: 4198190 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2389. Min Range: -3.2389
Max Act: 3.0026. Min Act: -0.1700
Data Index: 145462 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19