Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3571 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.4141. Min Act: -0.1700
Data Index: 133066 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.3828. Min Act: -0.1700
Data Index: 2136 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.3828. Min Act: -0.1700
Data Index: 7479836 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.2891. Min Act: -0.1700
Data Index: 2130835 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.2891. Min Act: -0.1700
Data Index: 7242783 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.2891. Min Act: -0.1700
Data Index: 1657953 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.2578. Min Act: -0.1700
Data Index: 341388 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.2578. Min Act: -0.1700
Data Index: 556374 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.2578. Min Act: -0.1700
Data Index: 7324767 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.2578. Min Act: -0.1700
Data Index: 6078108 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.2266. Min Act: -0.1700
Data Index: 3991115 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.2266. Min Act: -0.1700
Data Index: 7648766 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.1953. Min Act: -0.1700
Data Index: 4124072 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.1953. Min Act: -0.1700
Data Index: 7897691 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.1953. Min Act: -0.1700
Data Index: 246224 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.1953. Min Act: -0.1700
Data Index: 145778 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.1641. Min Act: -0.1700
Data Index: 3925504 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.1641. Min Act: -0.1700
Data Index: 533002 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.1641. Min Act: -0.1700
Data Index: 71429 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4141. Min Range: -6.4141
Max Act: 6.1641. Min Act: -0.1700
Data Index: 7402960 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19