Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 892 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6144. Min Range: -12.6144
Max Act: 12.6144. Min Act: -0.1700
Data Index: 843830 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6144. Min Range: -12.6144
Max Act: 12.4269. Min Act: -0.1700
Data Index: 83255 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6144. Min Range: -12.6144
Max Act: 12.2394. Min Act: -0.1700
Data Index: 5137199 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6144. Min Range: -12.6144
Max Act: 12.1769. Min Act: -0.1700
Data Index: 91784 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6144. Min Range: -12.6144
Max Act: 12.1144. Min Act: -0.1700
Data Index: 3567943 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6144. Min Range: -12.6144
Max Act: 12.1144. Min Act: -0.1700
Data Index: 2133529 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6144. Min Range: -12.6144
Max Act: 12.0519. Min Act: -0.1700
Data Index: 5690035 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6144. Min Range: -12.6144
Max Act: 11.9894. Min Act: -0.1700
Data Index: 7416663 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6144. Min Range: -12.6144
Max Act: 11.9269. Min Act: -0.1700
Data Index: 6376960 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6144. Min Range: -12.6144
Max Act: 11.8644. Min Act: -0.1700
Data Index: 3967460 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6144. Min Range: -12.6144
Max Act: 11.8019. Min Act: -0.1700
Data Index: 859971 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6144. Min Range: -12.6144
Max Act: 11.8019. Min Act: -0.1700
Data Index: 981979 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6144. Min Range: -12.6144
Max Act: 11.7394. Min Act: -0.1700
Data Index: 6216093 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6144. Min Range: -12.6144
Max Act: 11.8019. Min Act: -0.1700
Data Index: 423521 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6144. Min Range: -12.6144
Max Act: 11.7394. Min Act: -0.1700
Data Index: 821365 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6144. Min Range: -12.6144
Max Act: 11.7394. Min Act: -0.1700
Data Index: 4167002 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6144. Min Range: -12.6144
Max Act: 11.7394. Min Act: -0.1700
Data Index: 6866818 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6144. Min Range: -12.6144
Max Act: 11.7394. Min Act: -0.1700
Data Index: 4003538 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6144. Min Range: -12.6144
Max Act: 11.7394. Min Act: -0.1700
Data Index: 2487015 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6144. Min Range: -12.6144
Max Act: 11.7394. Min Act: -0.1700
Data Index: 5394123 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19