Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8094. Min Range: -7.8094
Max Act: 7.8094. Min Act: -0.1700
Data Index: 1020911 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8094. Min Range: -7.8094
Max Act: 7.2782. Min Act: -0.1700
Data Index: 4371820 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8094. Min Range: -7.8094
Max Act: 7.0282. Min Act: -0.1700
Data Index: 6081996 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8094. Min Range: -7.8094
Max Act: 7.0282. Min Act: -0.1700
Data Index: 7500075 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8094. Min Range: -7.8094
Max Act: 7.0282. Min Act: -0.1700
Data Index: 6051772 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.9969. Min Act: -0.1700
Data Index: 4302062 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.9344. Min Act: -0.1700
Data Index: 6720641 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.9032. Min Act: -0.1700
Data Index: 1638102 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.8094. Min Act: -0.1700
Data Index: 3158359 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.8094. Min Act: -0.1700
Data Index: 3561352 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.8094. Min Act: -0.1700
Data Index: 8299894 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.7782. Min Act: -0.1700
Data Index: 100613 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.7782. Min Act: -0.1700
Data Index: 6996931 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.7469. Min Act: -0.1700
Data Index: 5634822 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.6844. Min Act: -0.1700
Data Index: 8417315 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.7157. Min Act: -0.1700
Data Index: 5669555 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.6532. Min Act: -0.1700
Data Index: 5138939 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.6219. Min Act: -0.1700
Data Index: 1916491 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.6532. Min Act: -0.1700
Data Index: 189487 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8094. Min Range: -7.8094
Max Act: 6.6219. Min Act: -0.1700
Data Index: 8280626 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19