Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5682 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.6764. Min Act: -0.1700
Data Index: 3542920 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.5514. Min Act: -0.1700
Data Index: 4099154 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.4577. Min Act: -0.1700
Data Index: 739670 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.3952. Min Act: -0.1700
Data Index: 6181629 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.3952. Min Act: -0.1700
Data Index: 7991216 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.2702. Min Act: -0.1700
Data Index: 3547855 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.2389. Min Act: -0.1700
Data Index: 4043424 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.2389. Min Act: -0.1700
Data Index: 6259418 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.2077. Min Act: -0.1700
Data Index: 5026704 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.1452. Min Act: -0.1700
Data Index: 8282617 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.1139. Min Act: -0.1700
Data Index: 8000660 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.0827. Min Act: -0.1700
Data Index: 848849 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.0514. Min Act: -0.1700
Data Index: 8199463 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.0827. Min Act: -0.1700
Data Index: 1251795 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.0514. Min Act: -0.1700
Data Index: 1570326 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6764. Min Range: -6.6764
Max Act: 6.0514. Min Act: -0.1700
Data Index: 723759 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6764. Min Range: -6.6764
Max Act: 5.9889. Min Act: -0.1700
Data Index: 5980274 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6764. Min Range: -6.6764
Max Act: 5.9577. Min Act: -0.1700
Data Index: 3600589 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6764. Min Range: -6.6764
Max Act: 5.9577. Min Act: -0.1700
Data Index: 1617904 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6764. Min Range: -6.6764
Max Act: 5.9577. Min Act: -0.1700
Data Index: 1405239 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19