Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0182. Min Range: -8.0182
Max Act: 8.0182. Min Act: -0.1700
Data Index: 3487970 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.8932. Min Act: -0.1700
Data Index: 6870594 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.9245. Min Act: -0.1700
Data Index: 3545873 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.7682. Min Act: -0.1700
Data Index: 6540139 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.6745. Min Act: -0.1700
Data Index: 4723262 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.6120. Min Act: -0.1700
Data Index: 7207354 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.5807. Min Act: -0.1700
Data Index: 5513002 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.5807. Min Act: -0.1700
Data Index: 8084491 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.5807. Min Act: -0.1700
Data Index: 5416335 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.4870. Min Act: -0.1700
Data Index: 291512 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.4245. Min Act: -0.1700
Data Index: 2725235 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.3932. Min Act: -0.1700
Data Index: 1797353 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.3307. Min Act: -0.1700
Data Index: 5653441 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.3620. Min Act: -0.1700
Data Index: 1652869 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.2995. Min Act: -0.1700
Data Index: 764092 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.3307. Min Act: -0.1700
Data Index: 8763857 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.3620. Min Act: -0.1700
Data Index: 5691649 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.2995. Min Act: -0.1700
Data Index: 1797356 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.2995. Min Act: -0.1700
Data Index: 7551805 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.2995. Min Act: -0.1700
Data Index: 7646287 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19