Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3946 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.8344. Min Act: -0.1700
Data Index: 7399646 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.8032. Min Act: -0.1700
Data Index: 1754193 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.6782. Min Act: -0.1700
Data Index: 5118181 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.5844. Min Act: -0.1700
Data Index: 8230430 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.4907. Min Act: -0.1700
Data Index: 2817938 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.4907. Min Act: -0.1700
Data Index: 7156881 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.3657. Min Act: -0.1700
Data Index: 6666621 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.3657. Min Act: -0.1700
Data Index: 6180391 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.3657. Min Act: -0.1700
Data Index: 5847097 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.3344. Min Act: -0.1700
Data Index: 3444790 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.3032. Min Act: -0.1700
Data Index: 1678424 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.3344. Min Act: -0.1700
Data Index: 1581995 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.3032. Min Act: -0.1700
Data Index: 1498009 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.3032. Min Act: -0.1700
Data Index: 2909994 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.3032. Min Act: -0.1700
Data Index: 5741291 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.3032. Min Act: -0.1700
Data Index: 3070072 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.3032. Min Act: -0.1700
Data Index: 1566596 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.3032. Min Act: -0.1700
Data Index: 1352252 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.2719. Min Act: -0.1700
Data Index: 483224 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8344. Min Range: -7.8344
Max Act: 7.2719. Min Act: -0.1700
Data Index: 1351581 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19