Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2264. Min Range: -7.2264
Max Act: 7.2264. Min Act: -0.1700
Data Index: 8711771 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2264. Min Range: -7.2264
Max Act: 7.1952. Min Act: -0.1700
Data Index: 4236959 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.9452. Min Act: -0.1700
Data Index: 1998325 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.9139. Min Act: -0.1700
Data Index: 1393696 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.8827. Min Act: -0.1700
Data Index: 3672188 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.8827. Min Act: -0.1700
Data Index: 8628137 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.8514. Min Act: -0.1700
Data Index: 8609033 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.8514. Min Act: -0.1700
Data Index: 5677759 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.7889. Min Act: -0.1700
Data Index: 6163371 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.6639. Min Act: -0.1700
Data Index: 3848151 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.6327. Min Act: -0.1700
Data Index: 7650514 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.6327. Min Act: -0.1700
Data Index: 6685301 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.5702. Min Act: -0.1700
Data Index: 4214491 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.4764. Min Act: -0.1700
Data Index: 6318220 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.5077. Min Act: -0.1700
Data Index: 3009723 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.4764. Min Act: -0.1700
Data Index: 5381589 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.4764. Min Act: -0.1700
Data Index: 304303 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.4452. Min Act: -0.1700
Data Index: 7404317 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.5077. Min Act: -0.1700
Data Index: 1277622 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2264. Min Range: -7.2264
Max Act: 6.4764. Min Act: -0.1700
Data Index: 111101 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19