Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3986 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.2911. Min Act: -0.1700
Data Index: 748811 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.2911. Min Act: -0.1700
Data Index: 1363616 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.2286. Min Act: -0.1700
Data Index: 8776931 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.1974. Min Act: -0.1700
Data Index: 3461993 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.1974. Min Act: -0.1700
Data Index: 8281561 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.1661. Min Act: -0.1700
Data Index: 1933683 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.1349. Min Act: -0.1700
Data Index: 1363614 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.0724. Min Act: -0.1700
Data Index: 5144810 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.0724. Min Act: -0.1700
Data Index: 1210459 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.0411. Min Act: -0.1700
Data Index: 1383065 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.0099. Min Act: -0.1700
Data Index: 5634590 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.0411. Min Act: -0.1700
Data Index: 6732268 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.0724. Min Act: -0.1700
Data Index: 1513323 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.0099. Min Act: -0.1700
Data Index: 7942489 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.0099. Min Act: -0.1700
Data Index: 6535294 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.0099. Min Act: -0.1700
Data Index: 591607 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.0099. Min Act: -0.1700
Data Index: 7591900 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.0099. Min Act: -0.1700
Data Index: 1182190 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2911. Min Range: -5.2911
Max Act: 5.0411. Min Act: -0.1700
Data Index: 5128021 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2911. Min Range: -5.2911
Max Act: 4.9786. Min Act: -0.1700
Data Index: 2995542 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19