Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1805 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.0730. Min Range: -6.0730
Max Act: 6.0730. Min Act: -0.1700
Data Index: 5390754 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0730. Min Range: -6.0730
Max Act: 6.0105. Min Act: -0.1700
Data Index: 5134310 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.9793. Min Act: -0.1700
Data Index: 5629050 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.8855. Min Act: -0.1700
Data Index: 6300223 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.8543. Min Act: -0.1700
Data Index: 5566863 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.8543. Min Act: -0.1700
Data Index: 6170345 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.8543. Min Act: -0.1700
Data Index: 707137 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.8543. Min Act: -0.1700
Data Index: 4704108 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.8230. Min Act: -0.1700
Data Index: 5820651 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.8230. Min Act: -0.1700
Data Index: 3772330 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.7605. Min Act: -0.1700
Data Index: 4102282 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.7605. Min Act: -0.1700
Data Index: 8731906 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.7605. Min Act: -0.1700
Data Index: 1601030 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.7293. Min Act: -0.1700
Data Index: 2015605 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.6668. Min Act: -0.1700
Data Index: 4443317 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.6668. Min Act: -0.1700
Data Index: 7535725 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.6668. Min Act: -0.1700
Data Index: 3712184 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.6668. Min Act: -0.1700
Data Index: 8121981 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.6668. Min Act: -0.1700
Data Index: 1246732 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0730. Min Range: -6.0730
Max Act: 5.6980. Min Act: -0.1700
Data Index: 276301 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19