Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3295 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.4043. Min Act: -0.1700
Data Index: 3548354 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4043. Min Range: -5.4043
Max Act: 5.0293. Min Act: -0.1700
Data Index: 7872586 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.9981. Min Act: -0.1700
Data Index: 7641133 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.9981. Min Act: -0.1700
Data Index: 2302956 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.9668. Min Act: -0.1700
Data Index: 2953763 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.9668. Min Act: -0.1700
Data Index: 40144 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8731. Min Act: -0.1700
Data Index: 6187182 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.9043. Min Act: -0.1700
Data Index: 1798680 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8731. Min Act: -0.1700
Data Index: 8579052 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.9043. Min Act: -0.1700
Data Index: 5236219 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8418. Min Act: -0.1700
Data Index: 4832944 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8418. Min Act: -0.1700
Data Index: 4742711 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8106. Min Act: -0.1700
Data Index: 7367372 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8731. Min Act: -0.1700
Data Index: 6692417 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8418. Min Act: -0.1700
Data Index: 1495085 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8106. Min Act: -0.1700
Data Index: 6045230 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.8418. Min Act: -0.1700
Data Index: 3084472 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.7793. Min Act: -0.1700
Data Index: 4564004 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.7793. Min Act: -0.1700
Data Index: 3129265 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4043. Min Range: -5.4043
Max Act: 4.7793. Min Act: -0.1700
Data Index: 7803514 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19