Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2711 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.8746. Min Act: -0.1700
Data Index: 3697398 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.8270. Min Act: -0.1700
Data Index: 4294168 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.8111. Min Act: -0.1700
Data Index: 76600 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7951. Min Act: -0.1700
Data Index: 7308658 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7792. Min Act: -0.1700
Data Index: 3576468 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7633. Min Act: -0.1700
Data Index: 7032274 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7633. Min Act: -0.1700
Data Index: 1216012 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7633. Min Act: -0.1700
Data Index: 7104256 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7473. Min Act: -0.1700
Data Index: 2775728 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7473. Min Act: -0.1700
Data Index: 5893451 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7633. Min Act: -0.1700
Data Index: 77781 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7473. Min Act: -0.1700
Data Index: 3575120 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7473. Min Act: -0.1700
Data Index: 4294169 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7313. Min Act: -0.1700
Data Index: 669420 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7313. Min Act: -0.1700
Data Index: 8737248 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7313. Min Act: -0.1700
Data Index: 1209042 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7313. Min Act: -0.1700
Data Index: 3733686 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7153. Min Act: -0.1700
Data Index: 3929732 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7313. Min Act: -0.1700
Data Index: 6125281 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8746. Min Range: -2.8746
Max Act: 2.7313. Min Act: -0.1700
Data Index: 6067683 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19