Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.3072. Min Act: -0.1700
Data Index: 785269 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.2915. Min Act: -0.1700
Data Index: 4583338 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.2601. Min Act: -0.1700
Data Index: 3901361 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.2444. Min Act: -0.1700
Data Index: 8106611 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.2444. Min Act: -0.1700
Data Index: 6310324 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.2130. Min Act: -0.1700
Data Index: 1496777 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1973. Min Act: -0.1700
Data Index: 5187597 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1973. Min Act: -0.1700
Data Index: 8568038 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1973. Min Act: -0.1700
Data Index: 2002729 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1658. Min Act: -0.1700
Data Index: 8128392 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1815. Min Act: -0.1700
Data Index: 3913543 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1658. Min Act: -0.1700
Data Index: 7725940 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1500. Min Act: -0.1700
Data Index: 7851361 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1500. Min Act: -0.1700
Data Index: 8468068 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1500. Min Act: -0.1700
Data Index: 1510169 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1343. Min Act: -0.1700
Data Index: 4429137 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1343. Min Act: -0.1700
Data Index: 4934677 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1343. Min Act: -0.1700
Data Index: 4962408 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1028. Min Act: -0.1700
Data Index: 4075256 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3072. Min Range: -3.3072
Max Act: 3.1186. Min Act: -0.1700
Data Index: 3706679 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19