Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.9824. Min Act: -0.1700
Data Index: 4958568 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.9512. Min Act: -0.1700
Data Index: 8641672 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8886. Min Act: -0.1700
Data Index: 7456831 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8574. Min Act: -0.1700
Data Index: 6662067 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.7948. Min Act: -0.1700
Data Index: 3491501 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.7636. Min Act: -0.1700
Data Index: 5912505 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.7166. Min Act: -0.1700
Data Index: 2783048 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.7166. Min Act: -0.1700
Data Index: 703415 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.7010. Min Act: -0.1700
Data Index: 7571488 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.6854. Min Act: -0.1700
Data Index: 5444080 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.6854. Min Act: -0.1700
Data Index: 5687197 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.6697. Min Act: -0.1700
Data Index: 7841440 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.6854. Min Act: -0.1700
Data Index: 8712854 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.6384. Min Act: -0.1700
Data Index: 4782448 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.6384. Min Act: -0.1700
Data Index: 2790858 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.6384. Min Act: -0.1700
Data Index: 8532968 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.6071. Min Act: -0.1700
Data Index: 2926430 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.5915. Min Act: -0.1700
Data Index: 8754372 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.5915. Min Act: -0.1700
Data Index: 2783049 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.5915. Min Act: -0.1700
Data Index: 3022247 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19