Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.8736. Min Act: -0.1700
Data Index: 7240123 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.4986. Min Act: -0.1700
Data Index: 2102755 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.3736. Min Act: -0.1700
Data Index: 2602278 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.3736. Min Act: -0.1700
Data Index: 1160031 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.3736. Min Act: -0.1700
Data Index: 5710040 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.1861. Min Act: -0.1700
Data Index: 8520677 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.2486. Min Act: -0.1700
Data Index: 5457782 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.1861. Min Act: -0.1700
Data Index: 7240666 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.1861. Min Act: -0.1700
Data Index: 2599242 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.1236. Min Act: -0.1700
Data Index: 1121265 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.1236. Min Act: -0.1700
Data Index: 3217099 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.0611. Min Act: -0.1700
Data Index: 3456956 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.0611. Min Act: -0.1700
Data Index: 5345570 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.0611. Min Act: -0.1700
Data Index: 4158954 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.0611. Min Act: -0.1700
Data Index: 4983250 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.0611. Min Act: -0.1700
Data Index: 5782989 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.1236. Min Act: -0.1700
Data Index: 6012554 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8736. Min Range: -8.8736
Max Act: 7.9986. Min Act: -0.1700
Data Index: 394644 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8736. Min Range: -8.8736
Max Act: 7.9986. Min Act: -0.1700
Data Index: 1944839 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8736. Min Range: -8.8736
Max Act: 7.9986. Min Act: -0.1700
Data Index: 4192769 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19