Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1733. Min Range: -4.1733
Max Act: 4.1733. Min Act: -0.1700
Data Index: 4901944 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1733. Min Range: -4.1733
Max Act: 4.1420. Min Act: -0.1700
Data Index: 7237300 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1733. Min Range: -4.1733
Max Act: 4.1108. Min Act: -0.1700
Data Index: 5636988 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1733. Min Range: -4.1733
Max Act: 4.0795. Min Act: -0.1700
Data Index: 4901945 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1733. Min Range: -4.1733
Max Act: 4.1420. Min Act: -0.1700
Data Index: 3203024 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1733. Min Range: -4.1733
Max Act: 4.0482. Min Act: -0.1700
Data Index: 357807 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1733. Min Range: -4.1733
Max Act: 4.0482. Min Act: -0.1700
Data Index: 5791964 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1733. Min Range: -4.1733
Max Act: 4.0482. Min Act: -0.1700
Data Index: 339606 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1733. Min Range: -4.1733
Max Act: 4.0170. Min Act: -0.1700
Data Index: 3076609 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1733. Min Range: -4.1733
Max Act: 4.0170. Min Act: -0.1700
Data Index: 3895026 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1733. Min Range: -4.1733
Max Act: 3.9701. Min Act: -0.1700
Data Index: 1326 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1733. Min Range: -4.1733
Max Act: 4.0013. Min Act: -0.1700
Data Index: 18520 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1733. Min Range: -4.1733
Max Act: 3.9701. Min Act: -0.1700
Data Index: 6740949 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1733. Min Range: -4.1733
Max Act: 3.9545. Min Act: -0.1700
Data Index: 8237093 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1733. Min Range: -4.1733
Max Act: 3.9232. Min Act: -0.1700
Data Index: 970783 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1733. Min Range: -4.1733
Max Act: 3.9388. Min Act: -0.1700
Data Index: 4283180 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1733. Min Range: -4.1733
Max Act: 3.9232. Min Act: -0.1700
Data Index: 8374747 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1733. Min Range: -4.1733
Max Act: 3.9076. Min Act: -0.1700
Data Index: 6511887 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1733. Min Range: -4.1733
Max Act: 3.8763. Min Act: -0.1700
Data Index: 4223975 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1733. Min Range: -4.1733
Max Act: 3.8763. Min Act: -0.1700
Data Index: 1037818 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19