Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4875 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.7559. Min Act: -0.1700
Data Index: 904926 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.6309. Min Act: -0.1700
Data Index: 4017682 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.6309. Min Act: -0.1700
Data Index: 2831991 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.6309. Min Act: -0.1700
Data Index: 4635535 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.5996. Min Act: -0.1700
Data Index: 8390236 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.5996. Min Act: -0.1700
Data Index: 5902236 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.5996. Min Act: -0.1700
Data Index: 1272451 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.5684. Min Act: -0.1700
Data Index: 388443 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.5996. Min Act: -0.1700
Data Index: 3025242 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.5684. Min Act: -0.1700
Data Index: 2829627 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.5371. Min Act: -0.1700
Data Index: 1902310 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.5371. Min Act: -0.1700
Data Index: 237637 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.4746. Min Act: -0.1700
Data Index: 964109 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.5059. Min Act: -0.1700
Data Index: 7298265 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.4746. Min Act: -0.1700
Data Index: 1080935 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.4434. Min Act: -0.1700
Data Index: 7460633 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.4746. Min Act: -0.1700
Data Index: 6065217 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.4434. Min Act: -0.1700
Data Index: 3373526 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.4434. Min Act: -0.1700
Data Index: 6268277 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7559. Min Range: -4.7559
Max Act: 4.4121. Min Act: -0.1700
Data Index: 6636175 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19