Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5667 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.3716. Min Act: -0.1700
Data Index: 4586803 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.3389. Min Act: -0.1700
Data Index: 2916812 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.3225. Min Act: -0.1700
Data Index: 2940911 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.3061. Min Act: -0.1700
Data Index: 7114050 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.3061. Min Act: -0.1700
Data Index: 5436606 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2896. Min Act: -0.1700
Data Index: 7573180 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2896. Min Act: -0.1700
Data Index: 4864637 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2896. Min Act: -0.1698
Data Index: 5436605 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2896. Min Act: -0.1700
Data Index: 2245996 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2731. Min Act: -0.1700
Data Index: 2191148 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2731. Min Act: -0.1700
Data Index: 8022926 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2896. Min Act: -0.1700
Data Index: 171990 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2731. Min Act: -0.1700
Data Index: 4128758 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2566. Min Act: -0.1700
Data Index: 7774720 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2731. Min Act: -0.1700
Data Index: 7014005 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2401. Min Act: -0.1700
Data Index: 1280258 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2401. Min Act: -0.1700
Data Index: 5211943 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2401. Min Act: -0.1700
Data Index: 5813943 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2401. Min Act: -0.1700
Data Index: 3712317 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3716. Min Range: -2.3716
Max Act: 2.2235. Min Act: -0.1700
Data Index: 3884000 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19