Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3078 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4910. Min Range: -7.4910
Max Act: 7.4910. Min Act: -0.1700
Data Index: 4355261 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.8972. Min Act: -0.1700
Data Index: 8712144 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.8660. Min Act: -0.1700
Data Index: 181159 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.8972. Min Act: -0.1700
Data Index: 8174780 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.8972. Min Act: -0.1700
Data Index: 8315733 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.9285. Min Act: -0.1700
Data Index: 573697 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.8660. Min Act: -0.1700
Data Index: 8414874 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.7722. Min Act: -0.1700
Data Index: 8575607 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.7722. Min Act: -0.1700
Data Index: 2699369 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.7722. Min Act: -0.1700
Data Index: 582735 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.7722. Min Act: -0.1700
Data Index: 8442382 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.7410. Min Act: -0.1700
Data Index: 5790594 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.7410. Min Act: -0.1700
Data Index: 7033459 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.7097. Min Act: -0.1700
Data Index: 5702183 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.7097. Min Act: -0.1700
Data Index: 131874 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.7097. Min Act: -0.1700
Data Index: 5618594 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.6785. Min Act: -0.1700
Data Index: 2105226 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.6785. Min Act: -0.1700
Data Index: 2336287 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.6472. Min Act: -0.1700
Data Index: 4547225 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4910. Min Range: -7.4910
Max Act: 6.6472. Min Act: -0.1700
Data Index: 381161 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19