Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0730. Min Range: -8.0730
Max Act: 8.0730. Min Act: -0.1700
Data Index: 7277473 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0730. Min Range: -8.0730
Max Act: 8.0105. Min Act: -0.1700
Data Index: 1756628 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0730. Min Range: -8.0730
Max Act: 8.0105. Min Act: -0.1700
Data Index: 971329 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0730. Min Range: -8.0730
Max Act: 8.0105. Min Act: -0.1700
Data Index: 7118609 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.9168. Min Act: -0.1700
Data Index: 5664253 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.9480. Min Act: -0.1700
Data Index: 1370649 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.9168. Min Act: -0.1700
Data Index: 8614444 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.9168. Min Act: -0.1700
Data Index: 4937214 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.8543. Min Act: -0.1700
Data Index: 8486143 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.8230. Min Act: -0.1700
Data Index: 151539 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.7605. Min Act: -0.1700
Data Index: 2327483 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.8230. Min Act: -0.1700
Data Index: 6984699 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.7918. Min Act: -0.1700
Data Index: 1579679 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.7918. Min Act: -0.1700
Data Index: 6065616 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.7605. Min Act: -0.1700
Data Index: 3281784 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.7605. Min Act: -0.1700
Data Index: 8215257 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.7605. Min Act: -0.1700
Data Index: 720594 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.6980. Min Act: -0.1700
Data Index: 2012510 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.6668. Min Act: -0.1700
Data Index: 5568295 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0730. Min Range: -8.0730
Max Act: 7.6668. Min Act: -0.1700
Data Index: 424619 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19