Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1344 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.6231. Min Act: -0.1700
Data Index: 2106610 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.6231. Min Act: -0.1700
Data Index: 1382171 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.6231. Min Act: -0.1700
Data Index: 8276762 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.5918. Min Act: -0.1700
Data Index: 7366009 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.5606. Min Act: -0.1700
Data Index: 6881636 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.5606. Min Act: -0.1700
Data Index: 5456823 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.5293. Min Act: -0.1700
Data Index: 5705907 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.5293. Min Act: -0.1700
Data Index: 1641069 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.5606. Min Act: -0.1700
Data Index: 1607003 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.5293. Min Act: -0.1700
Data Index: 273288 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.5293. Min Act: -0.1700
Data Index: 1747391 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.5293. Min Act: -0.1700
Data Index: 3416462 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.4981. Min Act: -0.1700
Data Index: 5160613 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.4981. Min Act: -0.1700
Data Index: 4107220 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.4981. Min Act: -0.1700
Data Index: 6369504 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.4981. Min Act: -0.1700
Data Index: 5011878 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.5293. Min Act: -0.1700
Data Index: 407815 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.4668. Min Act: -0.1700
Data Index: 684293 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.4668. Min Act: -0.1700
Data Index: 2482190 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.4668. Min Act: -0.1700
Data Index: 3372938 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19