Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4888 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1869. Min Range: -6.1869
Max Act: 6.1869. Min Act: -0.1700
Data Index: 4156276 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.9057. Min Act: -0.1700
Data Index: 4353314 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.8119. Min Act: -0.1700
Data Index: 2552901 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.8119. Min Act: -0.1700
Data Index: 4929653 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7807. Min Act: -0.1700
Data Index: 5777942 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7494. Min Act: -0.1700
Data Index: 7409714 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7494. Min Act: -0.1700
Data Index: 714469 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7494. Min Act: -0.1700
Data Index: 2022206 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7182. Min Act: -0.1700
Data Index: 6567777 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7182. Min Act: -0.1700
Data Index: 6491693 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7182. Min Act: -0.1700
Data Index: 582065 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.6869. Min Act: -0.1700
Data Index: 1233399 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.7182. Min Act: -0.1700
Data Index: 2628977 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.6869. Min Act: -0.1700
Data Index: 542850 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.6869. Min Act: -0.1700
Data Index: 7363019 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.6557. Min Act: -0.1700
Data Index: 8521405 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.6557. Min Act: -0.1700
Data Index: 6933530 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.6244. Min Act: -0.1700
Data Index: 8198161 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.6557. Min Act: -0.1700
Data Index: 1185139 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1869. Min Range: -6.1869
Max Act: 5.6244. Min Act: -0.1700
Data Index: 5473018 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19