Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1649 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7859. Min Act: -0.1700
Data Index: 2382949 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7546. Min Act: -0.1700
Data Index: 7175264 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7233. Min Act: -0.1700
Data Index: 6711171 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7233. Min Act: -0.1700
Data Index: 4303685 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7077. Min Act: -0.1700
Data Index: 7937257 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7390. Min Act: -0.1700
Data Index: 5678096 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7077. Min Act: -0.1700
Data Index: 2056791 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7077. Min Act: -0.1700
Data Index: 7085383 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6920. Min Act: -0.1700
Data Index: 3857149 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7077. Min Act: -0.1700
Data Index: 2058002 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6920. Min Act: -0.1700
Data Index: 7734243 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6920. Min Act: -0.1700
Data Index: 632210 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6920. Min Act: -0.1700
Data Index: 8180716 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6920. Min Act: -0.1700
Data Index: 8632085 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6920. Min Act: -0.1700
Data Index: 326926 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6764. Min Act: -0.1700
Data Index: 7379810 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6607. Min Act: -0.1700
Data Index: 1420044 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6764. Min Act: -0.1700
Data Index: 709041 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6607. Min Act: -0.1700
Data Index: 6676095 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.6607. Min Act: -0.1700
Data Index: 6897782 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19