Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.2782. Min Act: -0.1700
Data Index: 7347894 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.3095. Min Act: -0.1700
Data Index: 1524451 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.2157. Min Act: -0.1700
Data Index: 2803324 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.2157. Min Act: -0.1700
Data Index: 4254828 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.1532. Min Act: -0.1700
Data Index: 4600843 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.1845. Min Act: -0.1700
Data Index: 7791356 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.1845. Min Act: -0.1700
Data Index: 3448962 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.1532. Min Act: -0.1700
Data Index: 1590566 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.1532. Min Act: -0.1700
Data Index: 8500971 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.1532. Min Act: -0.1700
Data Index: 5103882 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.1220. Min Act: -0.1700
Data Index: 8038599 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.0907. Min Act: -0.1700
Data Index: 8277705 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.1220. Min Act: -0.1700
Data Index: 1301416 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.0907. Min Act: -0.1700
Data Index: 6957494 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.0907. Min Act: -0.1700
Data Index: 5627937 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.1220. Min Act: -0.1700
Data Index: 7333919 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.0595. Min Act: -0.1700
Data Index: 1507217 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.0595. Min Act: -0.1700
Data Index: 1515886 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.0595. Min Act: -0.1700
Data Index: 3293042 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3095. Min Range: -6.3095
Max Act: 6.0595. Min Act: -0.1700
Data Index: 8702948 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19