Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3796 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.3259. Min Act: -0.1700
Data Index: 2057963 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.3571. Min Act: -0.1700
Data Index: 1896975 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.3571. Min Act: -0.1700
Data Index: 8187617 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.2634. Min Act: -0.1700
Data Index: 7779923 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.2634. Min Act: -0.1700
Data Index: 1889623 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.2321. Min Act: -0.1700
Data Index: 6414888 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.2321. Min Act: -0.1700
Data Index: 4054764 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.2321. Min Act: -0.1700
Data Index: 3395329 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.2321. Min Act: -0.1700
Data Index: 2669271 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.2321. Min Act: -0.1700
Data Index: 18469 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.2009. Min Act: -0.1700
Data Index: 1096382 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.2009. Min Act: -0.1700
Data Index: 1801239 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.2321. Min Act: -0.1700
Data Index: 7938134 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.1696. Min Act: -0.1700
Data Index: 8395966 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.1383. Min Act: -0.1700
Data Index: 5252937 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.1696. Min Act: -0.1700
Data Index: 3654400 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.1383. Min Act: -0.1700
Data Index: 5863652 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.1696. Min Act: -0.1700
Data Index: 6035325 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.1696. Min Act: -0.1700
Data Index: 6561354 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3571. Min Range: -4.3571
Max Act: 4.1383. Min Act: -0.1700
Data Index: 1311089 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19