Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0214. Min Range: -8.0214
Max Act: 8.0214. Min Act: -0.1700
Data Index: 7377471 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.6464. Min Act: -0.1700
Data Index: 7610095 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.5839. Min Act: -0.1700
Data Index: 4389573 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.5214. Min Act: -0.1700
Data Index: 4310889 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.5214. Min Act: -0.1700
Data Index: 6341798 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.5214. Min Act: -0.1700
Data Index: 721965 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.4589. Min Act: -0.1700
Data Index: 8720473 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.3964. Min Act: -0.1700
Data Index: 1632085 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.3964. Min Act: -0.1700
Data Index: 6261524 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.3964. Min Act: -0.1700
Data Index: 1312836 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.3964. Min Act: -0.1700
Data Index: 1896176 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.3964. Min Act: -0.1700
Data Index: 1006567 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.3339. Min Act: -0.1700
Data Index: 8117230 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.3339. Min Act: -0.1700
Data Index: 4755865 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.3027. Min Act: -0.1700
Data Index: 1000219 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.3027. Min Act: -0.1700
Data Index: 4796374 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.2714. Min Act: -0.1700
Data Index: 4365580 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.2714. Min Act: -0.1700
Data Index: 2691128 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.2714. Min Act: -0.1700
Data Index: 5554758 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0214. Min Range: -8.0214
Max Act: 7.2402. Min Act: -0.1700
Data Index: 5702767 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19