Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2738 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.8956. Min Act: -0.1700
Data Index: 8157029 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.8018. Min Act: -0.1700
Data Index: 140848 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.8018. Min Act: -0.1700
Data Index: 4357428 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.7706. Min Act: -0.1700
Data Index: 117873 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.7393. Min Act: -0.1700
Data Index: 7098189 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.7081. Min Act: -0.1700
Data Index: 2545544 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.6143. Min Act: -0.1700
Data Index: 6582108 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.6456. Min Act: -0.1700
Data Index: 833197 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.6143. Min Act: -0.1700
Data Index: 6274028 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.6143. Min Act: -0.1700
Data Index: 5366304 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.6143. Min Act: -0.1700
Data Index: 5385343 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.5831. Min Act: -0.1700
Data Index: 8794142 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.5831. Min Act: -0.1700
Data Index: 1969757 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.5831. Min Act: -0.1700
Data Index: 1572818 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.5831. Min Act: -0.1700
Data Index: 4877133 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.5831. Min Act: -0.1700
Data Index: 7725665 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.5831. Min Act: -0.1700
Data Index: 799011 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.5518. Min Act: -0.1700
Data Index: 7537655 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.5518. Min Act: -0.1700
Data Index: 8230129 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8956. Min Range: -5.8956
Max Act: 5.5518. Min Act: -0.1700
Data Index: 2320075 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19