Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3966 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2021. Min Range: -3.2021
Max Act: 3.2021. Min Act: -0.1700
Data Index: 3303418 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2021. Min Range: -3.2021
Max Act: 3.1077. Min Act: -0.1700
Data Index: 2089147 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2021. Min Range: -3.2021
Max Act: 3.0919. Min Act: -0.1700
Data Index: 5517389 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2021. Min Range: -3.2021
Max Act: 3.0761. Min Act: -0.1700
Data Index: 2708776 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2021. Min Range: -3.2021
Max Act: 3.0130. Min Act: -0.1700
Data Index: 6546672 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2021. Min Range: -3.2021
Max Act: 3.0130. Min Act: -0.1700
Data Index: 1729528 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9814. Min Act: -0.1700
Data Index: 158378 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9972. Min Act: -0.1700
Data Index: 4794691 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9814. Min Act: -0.1700
Data Index: 6028079 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9814. Min Act: -0.1700
Data Index: 8398197 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9814. Min Act: -0.1700
Data Index: 6890624 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9497. Min Act: -0.1700
Data Index: 6647306 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9497. Min Act: -0.1700
Data Index: 5596408 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9497. Min Act: -0.1700
Data Index: 4779513 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9339. Min Act: -0.1700
Data Index: 2768199 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9339. Min Act: -0.1700
Data Index: 5409019 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9497. Min Act: -0.1700
Data Index: 3035570 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9339. Min Act: -0.1700
Data Index: 2411774 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9339. Min Act: -0.1700
Data Index: 6326119 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2021. Min Range: -3.2021
Max Act: 2.9339. Min Act: -0.1700
Data Index: 5614475 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19