Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 186 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1576. Min Range: -7.1576
Max Act: 7.1576. Min Act: -0.1700
Data Index: 6258754 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1576. Min Range: -7.1576
Max Act: 7.0639. Min Act: -0.1700
Data Index: 2603931 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1576. Min Range: -7.1576
Max Act: 7.0014. Min Act: -0.1700
Data Index: 2315954 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.9701. Min Act: -0.1700
Data Index: 7420951 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.9701. Min Act: -0.1700
Data Index: 3442028 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.9389. Min Act: -0.1700
Data Index: 801937 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.8764. Min Act: -0.1700
Data Index: 8272774 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.8139. Min Act: -0.1700
Data Index: 6207307 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.8139. Min Act: -0.1700
Data Index: 2066812 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.7826. Min Act: -0.1700
Data Index: 3369671 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.7201. Min Act: -0.1700
Data Index: 4977680 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.7201. Min Act: -0.1700
Data Index: 8798067 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.7514. Min Act: -0.1700
Data Index: 4567072 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.7201. Min Act: -0.1700
Data Index: 2446699 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.6889. Min Act: -0.1700
Data Index: 8264547 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.6889. Min Act: -0.1700
Data Index: 8270074 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.6576. Min Act: -0.1700
Data Index: 429404 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.6576. Min Act: -0.1700
Data Index: 1343801 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.6889. Min Act: -0.1700
Data Index: 7763584 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1576. Min Range: -7.1576
Max Act: 6.6576. Min Act: -0.1700
Data Index: 4980101 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19