Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3092. Min Range: -5.3092
Max Act: 5.3092. Min Act: -0.1700
Data Index: 6229500 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3092. Min Range: -5.3092
Max Act: 5.3092. Min Act: -0.1700
Data Index: 922981 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3092. Min Range: -5.3092
Max Act: 5.2779. Min Act: -0.1700
Data Index: 2733 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3092. Min Range: -5.3092
Max Act: 5.2467. Min Act: -0.1700
Data Index: 3956581 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3092. Min Range: -5.3092
Max Act: 5.2154. Min Act: -0.1700
Data Index: 2791090 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3092. Min Range: -5.3092
Max Act: 5.1842. Min Act: -0.1700
Data Index: 922982 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3092. Min Range: -5.3092
Max Act: 5.2154. Min Act: -0.1700
Data Index: 7714694 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3092. Min Range: -5.3092
Max Act: 5.1217. Min Act: -0.1700
Data Index: 7918792 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3092. Min Range: -5.3092
Max Act: 5.0592. Min Act: -0.1700
Data Index: 7099049 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3092. Min Range: -5.3092
Max Act: 5.0592. Min Act: -0.1700
Data Index: 5642279 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3092. Min Range: -5.3092
Max Act: 5.0279. Min Act: -0.1700
Data Index: 4540519 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3092. Min Range: -5.3092
Max Act: 4.9967. Min Act: -0.1700
Data Index: 4871468 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3092. Min Range: -5.3092
Max Act: 4.9967. Min Act: -0.1700
Data Index: 2759495 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3092. Min Range: -5.3092
Max Act: 4.9967. Min Act: -0.1700
Data Index: 8481003 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3092. Min Range: -5.3092
Max Act: 4.9342. Min Act: -0.1700
Data Index: 6458085 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3092. Min Range: -5.3092
Max Act: 4.9654. Min Act: -0.1700
Data Index: 6400566 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3092. Min Range: -5.3092
Max Act: 4.9967. Min Act: -0.1700
Data Index: 8481002 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3092. Min Range: -5.3092
Max Act: 4.9654. Min Act: -0.1700
Data Index: 6391515 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3092. Min Range: -5.3092
Max Act: 4.9654. Min Act: -0.1700
Data Index: 6665736 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3092. Min Range: -5.3092
Max Act: 4.9967. Min Act: -0.1700
Data Index: 5642276 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19