Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1605 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7657. Min Act: -0.1700
Data Index: 1355381 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7657. Min Act: -0.1700
Data Index: 2871983 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7657. Min Act: -0.1700
Data Index: 152086 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7657. Min Act: -0.1700
Data Index: 1466866 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7484. Min Act: -0.1700
Data Index: 3284092 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7484. Min Act: -0.1700
Data Index: 7436714 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7138. Min Act: -0.1700
Data Index: 7082625 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7311. Min Act: -0.1700
Data Index: 300513 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7311. Min Act: -0.1700
Data Index: 8812049 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7311. Min Act: -0.1700
Data Index: 1068199 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7311. Min Act: -0.1700
Data Index: 720045 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7311. Min Act: -0.1700
Data Index: 4999329 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7138. Min Act: -0.1700
Data Index: 8626827 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7138. Min Act: -0.1700
Data Index: 2788473 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7311. Min Act: -0.1700
Data Index: 697762 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.7311. Min Act: -0.1700
Data Index: 6934328 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.6965. Min Act: -0.1700
Data Index: 3359414 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.6965. Min Act: -0.1700
Data Index: 6210610 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.6965. Min Act: -0.1700
Data Index: 6931339 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7657. Min Range: -1.7657
Max Act: 1.6965. Min Act: -0.1700
Data Index: 31363 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19