Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3159. Min Range: -5.3159
Max Act: 5.3159. Min Act: -0.1700
Data Index: 4332876 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3159. Min Range: -5.3159
Max Act: 5.2221. Min Act: -0.1700
Data Index: 6555077 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3159. Min Range: -5.3159
Max Act: 5.1596. Min Act: -0.1700
Data Index: 8684015 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3159. Min Range: -5.3159
Max Act: 5.1284. Min Act: -0.1700
Data Index: 8430667 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3159. Min Range: -5.3159
Max Act: 5.0034. Min Act: -0.1700
Data Index: 159311 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3159. Min Range: -5.3159
Max Act: 5.0034. Min Act: -0.1700
Data Index: 909953 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.9409. Min Act: -0.1700
Data Index: 1636423 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.9409. Min Act: -0.1700
Data Index: 5195145 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.9409. Min Act: -0.1700
Data Index: 5287864 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.9096. Min Act: -0.1700
Data Index: 6749212 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.9721. Min Act: -0.1700
Data Index: 4060038 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.9409. Min Act: -0.1700
Data Index: 4156123 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.9409. Min Act: -0.1700
Data Index: 3247141 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.9409. Min Act: -0.1700
Data Index: 8438030 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.9409. Min Act: -0.1700
Data Index: 8214134 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.8784. Min Act: -0.1700
Data Index: 5043718 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.9096. Min Act: -0.1700
Data Index: 6651598 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.8784. Min Act: -0.1700
Data Index: 5188433 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.8784. Min Act: -0.1700
Data Index: 1724009 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3159. Min Range: -5.3159
Max Act: 4.8784. Min Act: -0.1700
Data Index: 1318662 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19