Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4894 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0064. Min Range: -10.0064
Max Act: 10.0064. Min Act: -0.1700
Data Index: 5099290 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.8189. Min Act: -0.1700
Data Index: 1937363 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.5689. Min Act: -0.1700
Data Index: 6932132 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.5689. Min Act: -0.1700
Data Index: 4174537 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.5689. Min Act: -0.1700
Data Index: 6619551 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.4439. Min Act: -0.1700
Data Index: 5313254 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.3814. Min Act: -0.1700
Data Index: 1949686 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.3189. Min Act: -0.1700
Data Index: 2885986 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.3189. Min Act: -0.1700
Data Index: 8063725 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.3189. Min Act: -0.1700
Data Index: 7456985 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.3189. Min Act: -0.1700
Data Index: 634162 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.1939. Min Act: -0.1700
Data Index: 2576896 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.1939. Min Act: -0.1700
Data Index: 8307933 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.1314. Min Act: -0.1700
Data Index: 3863168 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.1314. Min Act: -0.1700
Data Index: 718647 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.1314. Min Act: -0.1700
Data Index: 1787373 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.1939. Min Act: -0.1700
Data Index: 1782549 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.1314. Min Act: -0.1700
Data Index: 1326011 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.1939. Min Act: -0.1700
Data Index: 868708 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0064. Min Range: -10.0064
Max Act: 9.1314. Min Act: -0.1700
Data Index: 6398966 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19