Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.7983. Min Act: -0.1700
Data Index: 6410053 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.7983. Min Act: -0.1700
Data Index: 1563156 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.7358. Min Act: -0.1700
Data Index: 8012935 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.7983. Min Act: -0.1700
Data Index: 3240099 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.7983. Min Act: -0.1700
Data Index: 2399858 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.5483. Min Act: -0.1700
Data Index: 3903279 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.5483. Min Act: -0.1700
Data Index: 748368 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.5483. Min Act: -0.1700
Data Index: 1193303 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.5483. Min Act: -0.1700
Data Index: 8079175 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.5483. Min Act: -0.1700
Data Index: 6155389 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.4858. Min Act: -0.1700
Data Index: 2843317 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.4858. Min Act: -0.1700
Data Index: 1057897 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.4233. Min Act: -0.1700
Data Index: 1812847 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.4233. Min Act: -0.1700
Data Index: 5716699 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.4233. Min Act: -0.1700
Data Index: 3389278 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.3608. Min Act: -0.1700
Data Index: 3055192 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.3608. Min Act: -0.1700
Data Index: 2204638 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.3608. Min Act: -0.1700
Data Index: 2070061 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.3608. Min Act: -0.1700
Data Index: 3607856 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7983. Min Range: -7.7983
Max Act: 7.3608. Min Act: -0.1700
Data Index: 3787547 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19