Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2500 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.9117. Min Act: -0.1700
Data Index: 8349353 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.7867. Min Act: -0.1700
Data Index: 2225797 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.7242. Min Act: -0.1700
Data Index: 599368 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.7555. Min Act: -0.1700
Data Index: 8729399 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.6930. Min Act: -0.1700
Data Index: 1646018 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5680. Min Act: -0.1700
Data Index: 4427488 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5992. Min Act: -0.1700
Data Index: 531810 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.6305. Min Act: -0.1700
Data Index: 7992949 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5680. Min Act: -0.1700
Data Index: 2523763 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5367. Min Act: -0.1700
Data Index: 482688 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5680. Min Act: -0.1700
Data Index: 4321991 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5680. Min Act: -0.1700
Data Index: 331824 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5680. Min Act: -0.1700
Data Index: 3984837 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5367. Min Act: -0.1700
Data Index: 3648789 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5367. Min Act: -0.1700
Data Index: 7111338 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5367. Min Act: -0.1700
Data Index: 5116464 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5055. Min Act: -0.1700
Data Index: 5849502 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5055. Min Act: -0.1700
Data Index: 318355 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5367. Min Act: -0.1700
Data Index: 3725616 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9117. Min Range: -4.9117
Max Act: 4.5367. Min Act: -0.1700
Data Index: 984988 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19