Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3830 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.7202. Min Act: -0.1700
Data Index: 2827614 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.5639. Min Act: -0.1700
Data Index: 3297580 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.5327. Min Act: -0.1700
Data Index: 5000179 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.5327. Min Act: -0.1700
Data Index: 121870 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.5014. Min Act: -0.1700
Data Index: 1288696 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.4702. Min Act: -0.1700
Data Index: 7921682 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.5014. Min Act: -0.1700
Data Index: 7924487 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.5014. Min Act: -0.1700
Data Index: 7921695 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.4702. Min Act: -0.1700
Data Index: 4368724 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.4702. Min Act: -0.1700
Data Index: 121879 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.4389. Min Act: -0.1700
Data Index: 5735622 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.4389. Min Act: -0.1700
Data Index: 5895570 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.4389. Min Act: -0.1700
Data Index: 7970509 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.3764. Min Act: -0.1700
Data Index: 3911447 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.3452. Min Act: -0.1700
Data Index: 3273358 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.3452. Min Act: -0.1700
Data Index: 3136954 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.3764. Min Act: -0.1700
Data Index: 38951 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.3139. Min Act: -0.1700
Data Index: 6416526 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.3452. Min Act: -0.1700
Data Index: 7177242 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.3452. Min Act: -0.1700
Data Index: 46445 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19