Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4027 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.2795. Min Act: -0.1700
Data Index: 6021693 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1858. Min Act: -0.1700
Data Index: 2094303 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1858. Min Act: -0.1700
Data Index: 2502015 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1858. Min Act: -0.1700
Data Index: 3452256 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1545. Min Act: -0.1700
Data Index: 3155927 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1545. Min Act: -0.1700
Data Index: 8165351 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1545. Min Act: -0.1700
Data Index: 2254372 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1233. Min Act: -0.1700
Data Index: 8350348 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1545. Min Act: -0.1700
Data Index: 1889813 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1233. Min Act: -0.1700
Data Index: 1689603 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1233. Min Act: -0.1700
Data Index: 75053 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.0920. Min Act: -0.1700
Data Index: 5813111 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1233. Min Act: -0.1700
Data Index: 8350353 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1233. Min Act: -0.1700
Data Index: 4355656 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1233. Min Act: -0.1700
Data Index: 8350356 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1233. Min Act: -0.1700
Data Index: 8350354 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1545. Min Act: -0.1700
Data Index: 2232625 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.1233. Min Act: -0.1700
Data Index: 5122638 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.0920. Min Act: -0.1700
Data Index: 32069 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2795. Min Range: -4.2795
Max Act: 4.0920. Min Act: -0.1700
Data Index: 4639707 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19