Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1677 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6242. Min Range: -8.6242
Max Act: 8.6242. Min Act: -0.1700
Data Index: 842775 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6242. Min Range: -8.6242
Max Act: 8.2492. Min Act: -0.1700
Data Index: 4826910 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6242. Min Range: -8.6242
Max Act: 8.1242. Min Act: -0.1700
Data Index: 4461800 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.9992. Min Act: -0.1700
Data Index: 2127523 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.9992. Min Act: -0.1700
Data Index: 2547488 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.8742. Min Act: -0.1700
Data Index: 3339179 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.9367. Min Act: -0.1700
Data Index: 6591457 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.9992. Min Act: -0.1700
Data Index: 1696965 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.9367. Min Act: -0.1700
Data Index: 2973395 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.9367. Min Act: -0.1700
Data Index: 4586696 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.8117. Min Act: -0.1700
Data Index: 2094479 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.8117. Min Act: -0.1700
Data Index: 693454 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.8117. Min Act: -0.1700
Data Index: 1765068 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.8117. Min Act: -0.1700
Data Index: 1941643 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.8117. Min Act: -0.1700
Data Index: 3809930 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.8117. Min Act: -0.1700
Data Index: 6402772 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.7492. Min Act: -0.1700
Data Index: 4199577 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.7179. Min Act: -0.1700
Data Index: 7279168 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.7492. Min Act: -0.1700
Data Index: 1225551 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6242. Min Range: -8.6242
Max Act: 7.7179. Min Act: -0.1700
Data Index: 6626842 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19