Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2426 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2864. Min Range: -4.2864
Max Act: 4.2864. Min Act: -0.1700
Data Index: 1099975 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2864. Min Range: -4.2864
Max Act: 4.0676. Min Act: -0.1700
Data Index: 7022660 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2864. Min Range: -4.2864
Max Act: 4.0676. Min Act: -0.1700
Data Index: 7351472 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2864. Min Range: -4.2864
Max Act: 4.0364. Min Act: -0.1700
Data Index: 4232744 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2864. Min Range: -4.2864
Max Act: 4.0364. Min Act: -0.1700
Data Index: 2015800 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2864. Min Range: -4.2864
Max Act: 4.0364. Min Act: -0.1700
Data Index: 8093411 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2864. Min Range: -4.2864
Max Act: 4.0364. Min Act: -0.1700
Data Index: 3830393 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2864. Min Range: -4.2864
Max Act: 4.0364. Min Act: -0.1700
Data Index: 2216777 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2864. Min Range: -4.2864
Max Act: 3.9739. Min Act: -0.1700
Data Index: 650444 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2864. Min Range: -4.2864
Max Act: 3.9739. Min Act: -0.1700
Data Index: 784973 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2864. Min Range: -4.2864
Max Act: 3.9426. Min Act: -0.1700
Data Index: 2157489 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2864. Min Range: -4.2864
Max Act: 3.9426. Min Act: -0.1700
Data Index: 8180656 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2864. Min Range: -4.2864
Max Act: 3.9426. Min Act: -0.1700
Data Index: 7785079 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2864. Min Range: -4.2864
Max Act: 3.9426. Min Act: -0.1700
Data Index: 5689347 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2864. Min Range: -4.2864
Max Act: 3.9113. Min Act: -0.1700
Data Index: 6439651 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2864. Min Range: -4.2864
Max Act: 3.9426. Min Act: -0.1700
Data Index: 8003302 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2864. Min Range: -4.2864
Max Act: 3.9113. Min Act: -0.1700
Data Index: 5208652 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2864. Min Range: -4.2864
Max Act: 3.8801. Min Act: -0.1700
Data Index: 6028813 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2864. Min Range: -4.2864
Max Act: 3.8801. Min Act: -0.1700
Data Index: 7514134 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2864. Min Range: -4.2864
Max Act: 3.8801. Min Act: -0.1700
Data Index: 1275810 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19