Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6396 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.5746. Min Act: -0.1700
Data Index: 5994543 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.5121. Min Act: -0.1700
Data Index: 2982076 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.3871. Min Act: -0.1700
Data Index: 2769202 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.3246. Min Act: -0.1700
Data Index: 5475090 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.2621. Min Act: -0.1700
Data Index: 6892802 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.2621. Min Act: -0.1700
Data Index: 2735841 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.2309. Min Act: -0.1700
Data Index: 715765 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1996. Min Act: -0.1700
Data Index: 6256953 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1684. Min Act: -0.1700
Data Index: 5920960 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1684. Min Act: -0.1700
Data Index: 7902882 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1996. Min Act: -0.1700
Data Index: 8295808 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1371. Min Act: -0.1700
Data Index: 5356273 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1371. Min Act: -0.1700
Data Index: 7368356 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1059. Min Act: -0.1700
Data Index: 984034 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1059. Min Act: -0.1700
Data Index: 5700459 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1059. Min Act: -0.1700
Data Index: 4998767 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.0746. Min Act: -0.1700
Data Index: 5680868 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1059. Min Act: -0.1700
Data Index: 3699925 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1059. Min Act: -0.1700
Data Index: 4665787 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.0746. Min Act: -0.1700
Data Index: 2614032 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19