Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2861 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.2144. Min Act: -0.1700
Data Index: 5467508 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.1207. Min Act: -0.1700
Data Index: 3055395 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9957. Min Act: -0.1700
Data Index: 1408892 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9644. Min Act: -0.1700
Data Index: 7324729 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9332. Min Act: -0.1700
Data Index: 8198935 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 6597432 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 3664422 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 5290009 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 8170584 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 8260296 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8707. Min Act: -0.1700
Data Index: 6544304 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8707. Min Act: -0.1700
Data Index: 5467659 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8394. Min Act: -0.1700
Data Index: 8393183 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8394. Min Act: -0.1700
Data Index: 4649828 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8082. Min Act: -0.1700
Data Index: 5941678 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8082. Min Act: -0.1700
Data Index: 5648826 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8082. Min Act: -0.1700
Data Index: 3169560 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7457. Min Act: -0.1700
Data Index: 6938656 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7457. Min Act: -0.1700
Data Index: 6690516 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7144. Min Act: -0.1700
Data Index: 5333827 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19