Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6318 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.8492. Min Act: -0.1700
Data Index: 3452768 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.5367. Min Act: -0.1700
Data Index: 4177020 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.4117. Min Act: -0.1700
Data Index: 7188902 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.3804. Min Act: -0.1700
Data Index: 8583186 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.3179. Min Act: -0.1700
Data Index: 8831645 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.2867. Min Act: -0.1700
Data Index: 8526810 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.2554. Min Act: -0.1700
Data Index: 5392763 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.2554. Min Act: -0.1700
Data Index: 4920325 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.2242. Min Act: -0.1700
Data Index: 453811 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.2242. Min Act: -0.1700
Data Index: 2443481 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.1929. Min Act: -0.1700
Data Index: 5335853 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.1617. Min Act: -0.1700
Data Index: 6665433 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.1929. Min Act: -0.1700
Data Index: 4606942 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.1304. Min Act: -0.1700
Data Index: 1986818 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.1304. Min Act: -0.1700
Data Index: 4266905 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.0992. Min Act: -0.1700
Data Index: 7950834 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.0992. Min Act: -0.1700
Data Index: 7933409 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.0992. Min Act: -0.1700
Data Index: 4681917 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.0992. Min Act: -0.1700
Data Index: 5897116 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8492. Min Range: -5.8492
Max Act: 5.0992. Min Act: -0.1700
Data Index: 5121767 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19