Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 511 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.8521. Min Act: -0.1700
Data Index: 5278893 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.6021. Min Act: -0.1700
Data Index: 7733047 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.5396. Min Act: -0.1700
Data Index: 3580220 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.4771. Min Act: -0.1700
Data Index: 4075898 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.4771. Min Act: -0.1700
Data Index: 1335183 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.4771. Min Act: -0.1700
Data Index: 5821327 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.4771. Min Act: -0.1700
Data Index: 3230959 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.4146. Min Act: -0.1700
Data Index: 6358955 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.4146. Min Act: -0.1700
Data Index: 6043009 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.4146. Min Act: -0.1700
Data Index: 1851469 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.3521. Min Act: -0.1700
Data Index: 2148133 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.3521. Min Act: -0.1700
Data Index: 1867942 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.3521. Min Act: -0.1700
Data Index: 5152283 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.3521. Min Act: -0.1700
Data Index: 8118137 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.2896. Min Act: -0.1700
Data Index: 5414868 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.2271. Min Act: -0.1700
Data Index: 5126581 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.2896. Min Act: -0.1700
Data Index: 1905884 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.2896. Min Act: -0.1700
Data Index: 4547220 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.2896. Min Act: -0.1700
Data Index: 2585793 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8521. Min Range: -9.8521
Max Act: 9.2896. Min Act: -0.1700
Data Index: 1226058 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19