Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4003 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.4666. Min Act: -0.1700
Data Index: 4015212 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.4353. Min Act: -0.1700
Data Index: 8105017 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.4041. Min Act: -0.1700
Data Index: 7249703 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.3728. Min Act: -0.1700
Data Index: 3131379 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.3416. Min Act: -0.1700
Data Index: 4852804 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.3103. Min Act: -0.1700
Data Index: 1020958 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.3103. Min Act: -0.1700
Data Index: 7287750 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.3103. Min Act: -0.1700
Data Index: 3831319 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.2791. Min Act: -0.1700
Data Index: 408563 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.2166. Min Act: -0.1700
Data Index: 7372540 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.2166. Min Act: -0.1700
Data Index: 1369073 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.1853. Min Act: -0.1700
Data Index: 7077802 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.2166. Min Act: -0.1700
Data Index: 8665696 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.1541. Min Act: -0.1700
Data Index: 5461891 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.1228. Min Act: -0.1700
Data Index: 7793605 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.1228. Min Act: -0.1700
Data Index: 3177322 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.1228. Min Act: -0.1700
Data Index: 8688151 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.0916. Min Act: -0.1700
Data Index: 5999107 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.0916. Min Act: -0.1700
Data Index: 8350150 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4666. Min Range: -6.4666
Max Act: 6.0916. Min Act: -0.1700
Data Index: 7555807 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19