Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3684 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.7531. Min Act: -0.1700
Data Index: 7729840 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.6571. Min Act: -0.1700
Data Index: 6118459 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.6089. Min Act: -0.1700
Data Index: 6200264 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.6250. Min Act: -0.1700
Data Index: 364560 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5928. Min Act: -0.1700
Data Index: 4578493 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5928. Min Act: -0.1700
Data Index: 4083802 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5928. Min Act: -0.1700
Data Index: 7508116 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5606. Min Act: -0.1700
Data Index: 3704890 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5767. Min Act: -0.1700
Data Index: 8363836 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5606. Min Act: -0.1700
Data Index: 4182732 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5767. Min Act: -0.1700
Data Index: 577927 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5283. Min Act: -0.1700
Data Index: 5154051 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5444. Min Act: -0.1700
Data Index: 3594131 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5444. Min Act: -0.1700
Data Index: 6936537 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5444. Min Act: -0.1700
Data Index: 5218875 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5444. Min Act: -0.1700
Data Index: 5201052 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5444. Min Act: -0.1700
Data Index: 444463 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5283. Min Act: -0.1700
Data Index: 8710926 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5283. Min Act: -0.1700
Data Index: 6330038 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7531. Min Range: -2.7531
Max Act: 2.5121. Min Act: -0.1700
Data Index: 2663265 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19