Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2997. Min Range: -5.2997
Max Act: 5.2997. Min Act: -0.1700
Data Index: 4225076 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2997. Min Range: -5.2997
Max Act: 5.1747. Min Act: -0.1700
Data Index: 5596433 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2997. Min Range: -5.2997
Max Act: 5.0184. Min Act: -0.1700
Data Index: 5098265 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9872. Min Act: -0.1700
Data Index: 7421102 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9872. Min Act: -0.1700
Data Index: 6505086 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9559. Min Act: -0.1700
Data Index: 7421103 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9559. Min Act: -0.1700
Data Index: 3886770 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9559. Min Act: -0.1700
Data Index: 4778850 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9559. Min Act: -0.1700
Data Index: 837054 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9559. Min Act: -0.1700
Data Index: 6175233 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9559. Min Act: -0.1700
Data Index: 466714 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.9247. Min Act: -0.1700
Data Index: 1550426 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.8622. Min Act: -0.1700
Data Index: 4778851 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.8622. Min Act: -0.1700
Data Index: 3886769 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.8622. Min Act: -0.1700
Data Index: 1562063 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.8309. Min Act: -0.1700
Data Index: 4423455 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.8309. Min Act: -0.1700
Data Index: 2710191 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.7997. Min Act: -0.1700
Data Index: 266445 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.8309. Min Act: -0.1699
Data Index: 5388947 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2997. Min Range: -5.2997
Max Act: 4.8309. Min Act: -0.1700
Data Index: 3886771 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19