Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4325 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.4855. Min Act: -0.1700
Data Index: 3419131 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.3293. Min Act: -0.1700
Data Index: 6707532 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.3293. Min Act: -0.1700
Data Index: 4133342 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.3293. Min Act: -0.1700
Data Index: 1678868 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.2980. Min Act: -0.1700
Data Index: 2769957 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.2355. Min Act: -0.1700
Data Index: 4589987 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.2668. Min Act: -0.1700
Data Index: 8025077 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.2043. Min Act: -0.1700
Data Index: 2230335 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.2043. Min Act: -0.1700
Data Index: 6870989 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.2043. Min Act: -0.1700
Data Index: 5604418 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.2043. Min Act: -0.1700
Data Index: 805334 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.1418. Min Act: -0.1700
Data Index: 2378505 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.1730. Min Act: -0.1700
Data Index: 6195106 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.1730. Min Act: -0.1700
Data Index: 6010996 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.1730. Min Act: -0.1700
Data Index: 5407069 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.1730. Min Act: -0.1700
Data Index: 4942047 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.1418. Min Act: -0.1700
Data Index: 2697159 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.1418. Min Act: -0.1700
Data Index: 1880358 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.1418. Min Act: -0.1700
Data Index: 2433495 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4855. Min Range: -5.4855
Max Act: 5.1418. Min Act: -0.1700
Data Index: 6319675 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19