Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.5424. Min Act: -0.1700
Data Index: 8319697 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.5424. Min Act: -0.1700
Data Index: 381191 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.5112. Min Act: -0.1700
Data Index: 5948172 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.4174. Min Act: -0.1700
Data Index: 7302948 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.3549. Min Act: -0.1700
Data Index: 6006722 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.3549. Min Act: -0.1700
Data Index: 3670617 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.3549. Min Act: -0.1700
Data Index: 5253028 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.3549. Min Act: -0.1700
Data Index: 6474699 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.3549. Min Act: -0.1700
Data Index: 6324618 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.3549. Min Act: -0.1700
Data Index: 5938583 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.3237. Min Act: -0.1700
Data Index: 730711 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.3237. Min Act: -0.1700
Data Index: 5961378 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.3237. Min Act: -0.1700
Data Index: 586838 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.2924. Min Act: -0.1700
Data Index: 3306108 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.2612. Min Act: -0.1700
Data Index: 5024930 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.2612. Min Act: -0.1700
Data Index: 8806626 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.2612. Min Act: -0.1700
Data Index: 6934413 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.2612. Min Act: -0.1700
Data Index: 7846175 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.2299. Min Act: -0.1700
Data Index: 171615 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5424. Min Range: -5.5424
Max Act: 5.2299. Min Act: -0.1700
Data Index: 8450354 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19