Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2223 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0749. Min Range: -8.0749
Max Act: 8.0749. Min Act: -0.1700
Data Index: 7469424 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0749. Min Range: -8.0749
Max Act: 8.0436. Min Act: -0.1700
Data Index: 1027587 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.7936. Min Act: -0.1700
Data Index: 594177 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.6061. Min Act: -0.1700
Data Index: 2358357 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.5749. Min Act: -0.1700
Data Index: 2760900 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.5124. Min Act: -0.1700
Data Index: 3382529 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.5436. Min Act: -0.1700
Data Index: 3974491 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.4811. Min Act: -0.1700
Data Index: 6938392 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.5124. Min Act: -0.1700
Data Index: 3815619 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.4811. Min Act: -0.1700
Data Index: 402939 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.4811. Min Act: -0.1700
Data Index: 3708904 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.4499. Min Act: -0.1700
Data Index: 7342286 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.3874. Min Act: -0.1700
Data Index: 94091 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.4186. Min Act: -0.1700
Data Index: 4825141 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.3561. Min Act: -0.1700
Data Index: 4126115 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.3249. Min Act: -0.1700
Data Index: 8759787 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.3249. Min Act: -0.1700
Data Index: 5888745 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.2936. Min Act: -0.1700
Data Index: 94096 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.3249. Min Act: -0.1700
Data Index: 5770675 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0749. Min Range: -8.0749
Max Act: 7.2936. Min Act: -0.1700
Data Index: 7825770 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19