Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2713 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.5497. Min Act: -0.1700
Data Index: 4078546 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.4870. Min Act: -0.1700
Data Index: 56387 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.4714. Min Act: -0.1700
Data Index: 6428502 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.4557. Min Act: -0.1700
Data Index: 1808035 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.4557. Min Act: -0.1700
Data Index: 1076788 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.4400. Min Act: -0.1700
Data Index: 1327818 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.4244. Min Act: -0.1700
Data Index: 4046223 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.4244. Min Act: -0.1700
Data Index: 5262228 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.4087. Min Act: -0.1700
Data Index: 8464773 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.4087. Min Act: -0.1700
Data Index: 4599550 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.3930. Min Act: -0.1700
Data Index: 980126 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.3930. Min Act: -0.1700
Data Index: 5696492 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.3773. Min Act: -0.1700
Data Index: 4325623 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.3773. Min Act: -0.1700
Data Index: 2232467 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.3773. Min Act: -0.1700
Data Index: 1391368 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.3616. Min Act: -0.1700
Data Index: 2716550 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.3616. Min Act: -0.1700
Data Index: 1550076 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.3459. Min Act: -0.1700
Data Index: 1551069 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.3616. Min Act: -0.1700
Data Index: 2882054 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5497. Min Range: -3.5497
Max Act: 3.3616. Min Act: -0.1700
Data Index: 1796412 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19