Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 595 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.6295. Min Act: -0.1700
Data Index: 8006088 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.5357. Min Act: -0.1700
Data Index: 5722367 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.3795. Min Act: -0.1700
Data Index: 4863673 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.2857. Min Act: -0.1700
Data Index: 8666917 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.2545. Min Act: -0.1700
Data Index: 6791698 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.2232. Min Act: -0.1700
Data Index: 4998798 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.1920. Min Act: -0.1700
Data Index: 7007417 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.1920. Min Act: -0.1700
Data Index: 5734574 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.1607. Min Act: -0.1700
Data Index: 1282517 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.1607. Min Act: -0.1700
Data Index: 3035891 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.0982. Min Act: -0.1700
Data Index: 5135411 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.0982. Min Act: -0.1700
Data Index: 538425 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.0982. Min Act: -0.1700
Data Index: 8223205 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.0982. Min Act: -0.1700
Data Index: 6849354 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.0982. Min Act: -0.1700
Data Index: 5099309 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.0982. Min Act: -0.1700
Data Index: 7311866 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.0670. Min Act: -0.1700
Data Index: 3423614 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.0670. Min Act: -0.1700
Data Index: 4330097 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.0670. Min Act: -0.1700
Data Index: 2662583 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6295. Min Range: -5.6295
Max Act: 5.0982. Min Act: -0.1700
Data Index: 705 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19