Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.3267. Min Act: -0.1700
Data Index: 3851132 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.2482. Min Act: -0.1700
Data Index: 6931043 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.2168. Min Act: -0.1700
Data Index: 1246579 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.2168. Min Act: -0.1700
Data Index: 6451186 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.2168. Min Act: -0.1700
Data Index: 1367363 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.2168. Min Act: -0.1700
Data Index: 5453831 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.2168. Min Act: -0.1700
Data Index: 6224740 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.2168. Min Act: -0.1700
Data Index: 5929368 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.2168. Min Act: -0.1700
Data Index: 7574257 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.2011. Min Act: -0.1700
Data Index: 2838742 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.2168. Min Act: -0.1700
Data Index: 6848534 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.2011. Min Act: -0.1700
Data Index: 6964421 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.2011. Min Act: -0.1700
Data Index: 3159342 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.1853. Min Act: -0.1700
Data Index: 5889632 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.1853. Min Act: -0.1700
Data Index: 6459121 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.1696. Min Act: -0.1700
Data Index: 72802 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.1696. Min Act: -0.1700
Data Index: 1742326 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.1696. Min Act: -0.1700
Data Index: 487603 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.1696. Min Act: -0.1700
Data Index: 3478565 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3267. Min Range: -3.3267
Max Act: 3.1696. Min Act: -0.1700
Data Index: 5236345 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19