Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2562 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.6889. Min Act: -0.1700
Data Index: 4958218 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.3757. Min Act: -0.1700
Data Index: 1932508 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.3443. Min Act: -0.1700
Data Index: 4155851 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.3286. Min Act: -0.1700
Data Index: 6266719 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.2658. Min Act: -0.1700
Data Index: 4048077 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.2815. Min Act: -0.1700
Data Index: 4517463 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.2815. Min Act: -0.1700
Data Index: 5282883 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.2501. Min Act: -0.1700
Data Index: 4484441 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.2187. Min Act: -0.1700
Data Index: 1986257 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.2344. Min Act: -0.1700
Data Index: 5282902 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.1872. Min Act: -0.1700
Data Index: 7292281 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.2029. Min Act: -0.1700
Data Index: 3250944 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.1872. Min Act: -0.1700
Data Index: 6283985 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.2187. Min Act: -0.1700
Data Index: 5167146 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.2029. Min Act: -0.1700
Data Index: 682826 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.1715. Min Act: -0.1700
Data Index: 8375554 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.1872. Min Act: -0.1700
Data Index: 3053167 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.1872. Min Act: -0.1700
Data Index: 1406576 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.2029. Min Act: -0.1700
Data Index: 6098634 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6889. Min Range: -3.6889
Max Act: 3.1872. Min Act: -0.1700
Data Index: 1842923 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19