Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2710 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.6692. Min Act: -0.1700
Data Index: 8499696 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.6532. Min Act: -0.1700
Data Index: 5922696 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.6532. Min Act: -0.1700
Data Index: 1071552 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.6532. Min Act: -0.1700
Data Index: 5505240 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.6211. Min Act: -0.1700
Data Index: 5112332 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.6050. Min Act: -0.1700
Data Index: 8389344 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.6050. Min Act: -0.1700
Data Index: 4043885 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.6211. Min Act: -0.1700
Data Index: 5170189 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.5889. Min Act: -0.1700
Data Index: 8573115 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.5889. Min Act: -0.1700
Data Index: 5631239 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.6050. Min Act: -0.1700
Data Index: 4406143 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.5728. Min Act: -0.1700
Data Index: 341546 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.5728. Min Act: -0.1700
Data Index: 5354701 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.5728. Min Act: -0.1700
Data Index: 3465253 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.5566. Min Act: -0.1700
Data Index: 7281786 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.5566. Min Act: -0.1700
Data Index: 3955224 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.5405. Min Act: -0.1700
Data Index: 1689824 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.5405. Min Act: -0.1700
Data Index: 629044 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.5405. Min Act: -0.1700
Data Index: 2610601 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6692. Min Range: -2.6692
Max Act: 2.5566. Min Act: -0.1700
Data Index: 7017404 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19