Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 13 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.9187. Min Act: -0.1700
Data Index: 8110212 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.9187. Min Act: -0.1700
Data Index: 254269 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8760. Min Act: -0.1700
Data Index: 3311512 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8675. Min Act: -0.1700
Data Index: 1884675 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8675. Min Act: -0.1700
Data Index: 77721 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8589. Min Act: -0.1700
Data Index: 4427222 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8675. Min Act: -0.1700
Data Index: 4987924 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8589. Min Act: -0.1700
Data Index: 7735822 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8504. Min Act: -0.1700
Data Index: 2778618 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8418. Min Act: -0.1700
Data Index: 4485432 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8504. Min Act: -0.1700
Data Index: 8426911 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8332. Min Act: -0.1700
Data Index: 239552 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8418. Min Act: -0.1700
Data Index: 7876879 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8332. Min Act: -0.1700
Data Index: 2067726 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8332. Min Act: -0.1700
Data Index: 8236473 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8332. Min Act: -0.1700
Data Index: 6874283 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8246. Min Act: -0.1700
Data Index: 3721984 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8246. Min Act: -0.1700
Data Index: 6799997 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8246. Min Act: -0.1700
Data Index: 3098492 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9187. Min Range: -1.9187
Max Act: 1.8332. Min Act: -0.1700
Data Index: 7078443 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19