Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1411 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2752. Min Range: -3.2752
Max Act: 3.2752. Min Act: -0.1700
Data Index: 6614449 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.9917. Min Act: -0.1700
Data Index: 2262155 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.9759. Min Act: -0.1700
Data Index: 7886567 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.9917. Min Act: -0.1700
Data Index: 2214980 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.9601. Min Act: -0.1700
Data Index: 6395431 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.9442. Min Act: -0.1700
Data Index: 6357302 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.9284. Min Act: -0.1700
Data Index: 1003477 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.9442. Min Act: -0.1700
Data Index: 5525141 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.8650. Min Act: -0.1700
Data Index: 4722998 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.8808. Min Act: -0.1700
Data Index: 2214989 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.8650. Min Act: -0.1700
Data Index: 370533 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.8650. Min Act: -0.1700
Data Index: 6357282 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.8332. Min Act: -0.1700
Data Index: 5021001 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.8491. Min Act: -0.1700
Data Index: 7869598 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.8650. Min Act: -0.1700
Data Index: 7858133 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.8332. Min Act: -0.1700
Data Index: 8106859 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.8332. Min Act: -0.1700
Data Index: 2214978 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.8332. Min Act: -0.1700
Data Index: 682421 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.8173. Min Act: -0.1700
Data Index: 2555244 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2752. Min Range: -3.2752
Max Act: 2.8173. Min Act: -0.1700
Data Index: 7574960 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19