Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3139 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0646. Min Range: -5.0646
Max Act: 5.0646. Min Act: -0.1700
Data Index: 8128081 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.7834. Min Act: -0.1700
Data Index: 4484948 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.5959. Min Act: -0.1700
Data Index: 109806 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.5959. Min Act: -0.1700
Data Index: 8199359 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.5646. Min Act: -0.1700
Data Index: 1431088 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.5334. Min Act: -0.1700
Data Index: 3151251 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.5334. Min Act: -0.1700
Data Index: 5488168 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.5021. Min Act: -0.1700
Data Index: 4729858 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.5021. Min Act: -0.1700
Data Index: 1531587 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.4709. Min Act: -0.1700
Data Index: 6532298 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.4396. Min Act: -0.1700
Data Index: 337520 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.4084. Min Act: -0.1700
Data Index: 190512 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.4084. Min Act: -0.1700
Data Index: 4463772 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.4084. Min Act: -0.1700
Data Index: 5440292 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.3771. Min Act: -0.1700
Data Index: 5694094 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.3771. Min Act: -0.1700
Data Index: 668598 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.3771. Min Act: -0.1700
Data Index: 8650989 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.3771. Min Act: -0.1700
Data Index: 8622850 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.3459. Min Act: -0.1700
Data Index: 6657394 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0646. Min Range: -5.0646
Max Act: 4.3771. Min Act: -0.1700
Data Index: 511896 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19