Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4724 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.8975. Min Act: -0.1700
Data Index: 5477744 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.7724. Min Act: -0.1700
Data Index: 6849110 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.7411. Min Act: -0.1700
Data Index: 7519518 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.7098. Min Act: -0.1700
Data Index: 2509560 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.7411. Min Act: -0.1700
Data Index: 3129453 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.6785. Min Act: -0.1700
Data Index: 4849487 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.6159. Min Act: -0.1700
Data Index: 8765764 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.6159. Min Act: -0.1700
Data Index: 6573870 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.5533. Min Act: -0.1700
Data Index: 796163 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.5846. Min Act: -0.1700
Data Index: 5390367 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.5846. Min Act: -0.1700
Data Index: 850299 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.5846. Min Act: -0.1700
Data Index: 6821323 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.5846. Min Act: -0.1700
Data Index: 636808 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.6159. Min Act: -0.1700
Data Index: 1571816 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.5533. Min Act: -0.1700
Data Index: 8681493 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.5846. Min Act: -0.1700
Data Index: 5022486 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.5846. Min Act: -0.1700
Data Index: 1494526 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.5846. Min Act: -0.1700
Data Index: 7334954 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.5533. Min Act: -0.1700
Data Index: 7524134 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8975. Min Range: -3.8975
Max Act: 3.5533. Min Act: -0.1700
Data Index: 5799675 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19