Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1627 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.5776. Min Act: -0.1700
Data Index: 1810968 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.4526. Min Act: -0.1700
Data Index: 1716048 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.4214. Min Act: -0.1700
Data Index: 3985358 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.3901. Min Act: -0.1700
Data Index: 8225081 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.3901. Min Act: -0.1700
Data Index: 4983829 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.3276. Min Act: -0.1700
Data Index: 4924493 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.3276. Min Act: -0.1700
Data Index: 3362211 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2964. Min Act: -0.1700
Data Index: 8750871 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2651. Min Act: -0.1700
Data Index: 8515167 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2964. Min Act: -0.1700
Data Index: 5998458 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2964. Min Act: -0.1700
Data Index: 4296159 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2964. Min Act: -0.1700
Data Index: 5626892 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2651. Min Act: -0.1700
Data Index: 3704654 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2651. Min Act: -0.1700
Data Index: 3147924 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2651. Min Act: -0.1700
Data Index: 7580087 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2026. Min Act: -0.1700
Data Index: 2837613 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2339. Min Act: -0.1700
Data Index: 57997 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2339. Min Act: -0.1700
Data Index: 1810969 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2339. Min Act: -0.1700
Data Index: 1036171 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2339. Min Act: -0.1700
Data Index: 594949 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19