Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2998 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.3840. Min Act: -0.1700
Data Index: 3792758 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.3840. Min Act: -0.1700
Data Index: 5905576 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.3215. Min Act: -0.1700
Data Index: 932146 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.2590. Min Act: -0.1700
Data Index: 7340416 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.2278. Min Act: -0.1700
Data Index: 4891094 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.2590. Min Act: -0.1700
Data Index: 5141544 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.1653. Min Act: -0.1700
Data Index: 3357242 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.1653. Min Act: -0.1700
Data Index: 2008249 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.1653. Min Act: -0.1700
Data Index: 365373 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.1028. Min Act: -0.1700
Data Index: 2568385 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.1028. Min Act: -0.1700
Data Index: 5957522 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.1028. Min Act: -0.1700
Data Index: 8825701 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.1028. Min Act: -0.1700
Data Index: 5000397 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.0715. Min Act: -0.1700
Data Index: 8605684 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.0403. Min Act: -0.1700
Data Index: 7628582 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.0715. Min Act: -0.1700
Data Index: 5754989 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.0403. Min Act: -0.1700
Data Index: 1304017 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.0403. Min Act: -0.1700
Data Index: 1428284 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.0403. Min Act: -0.1700
Data Index: 4829629 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.0090. Min Act: -0.1700
Data Index: 7669618 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19