Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1654. Min Range: -4.1654
Max Act: 4.1654. Min Act: -0.1700
Data Index: 7243311 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.9466. Min Act: -0.1700
Data Index: 62787 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.9153. Min Act: -0.1700
Data Index: 7415353 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.9153. Min Act: -0.1700
Data Index: 7150683 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.9153. Min Act: -0.1700
Data Index: 2923510 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.8215. Min Act: -0.1700
Data Index: 5164924 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.7902. Min Act: -0.1700
Data Index: 6646941 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.7902. Min Act: -0.1700
Data Index: 172558 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.7590. Min Act: -0.1700
Data Index: 6011901 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.7433. Min Act: -0.1700
Data Index: 6671672 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.7433. Min Act: -0.1700
Data Index: 7841567 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.7277. Min Act: -0.1700
Data Index: 7363423 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.6807. Min Act: -0.1700
Data Index: 7741116 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.6807. Min Act: -0.1700
Data Index: 3884208 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.6807. Min Act: -0.1700
Data Index: 7206658 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.6651. Min Act: -0.1700
Data Index: 2604186 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.6964. Min Act: -0.1700
Data Index: 8249446 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.6495. Min Act: -0.1700
Data Index: 3512187 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.6651. Min Act: -0.1700
Data Index: 6923582 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1654. Min Range: -4.1654
Max Act: 3.6182. Min Act: -0.1700
Data Index: 8245948 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19