Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5208 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0149. Min Range: -8.0149
Max Act: 8.0149. Min Act: -0.1700
Data Index: 696656 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.7649. Min Act: -0.1700
Data Index: 3237386 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.7649. Min Act: -0.1700
Data Index: 4132019 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.7649. Min Act: -0.1700
Data Index: 8557495 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.7024. Min Act: -0.1700
Data Index: 2888188 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.7024. Min Act: -0.1700
Data Index: 8595534 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.6399. Min Act: -0.1700
Data Index: 7664996 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.6399. Min Act: -0.1700
Data Index: 3070158 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.7024. Min Act: -0.1700
Data Index: 8397115 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.6399. Min Act: -0.1700
Data Index: 7149334 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.5774. Min Act: -0.1700
Data Index: 3053953 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.5774. Min Act: -0.1700
Data Index: 3119651 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.5774. Min Act: -0.1700
Data Index: 7904396 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.5774. Min Act: -0.1700
Data Index: 7630149 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.5149. Min Act: -0.1700
Data Index: 5718359 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.5149. Min Act: -0.1700
Data Index: 4082633 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.5149. Min Act: -0.1700
Data Index: 881547 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.4836. Min Act: -0.1700
Data Index: 2032825 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.4836. Min Act: -0.1700
Data Index: 2463177 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0149. Min Range: -8.0149
Max Act: 7.4524. Min Act: -0.1700
Data Index: 3159831 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19