Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2754 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.3482. Min Act: -0.1700
Data Index: 7635159 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.3482. Min Act: -0.1700
Data Index: 7375048 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1920. Min Act: -0.1700
Data Index: 3202703 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2232. Min Act: -0.1700
Data Index: 8350130 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1920. Min Act: -0.1700
Data Index: 4558206 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1920. Min Act: -0.1700
Data Index: 3645437 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1295. Min Act: -0.1700
Data Index: 5782744 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1607. Min Act: -0.1700
Data Index: 8828633 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1607. Min Act: -0.1700
Data Index: 7340065 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1295. Min Act: -0.1700
Data Index: 4984989 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1295. Min Act: -0.1700
Data Index: 4404257 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1295. Min Act: -0.1700
Data Index: 6038472 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1295. Min Act: -0.1700
Data Index: 8454600 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0982. Min Act: -0.1700
Data Index: 6580880 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0982. Min Act: -0.1700
Data Index: 7288353 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0982. Min Act: -0.1700
Data Index: 8025811 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0982. Min Act: -0.1700
Data Index: 1042756 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0670. Min Act: -0.1700
Data Index: 373834 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0670. Min Act: -0.1700
Data Index: 2872925 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0670. Min Act: -0.1700
Data Index: 7768632 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19