Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0946. Min Range: -7.0946
Max Act: 7.0946. Min Act: -0.1700
Data Index: 6116845 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.8446. Min Act: -0.1700
Data Index: 1974581 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.5633. Min Act: -0.1700
Data Index: 5618589 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.5321. Min Act: -0.1700
Data Index: 275473 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.5008. Min Act: -0.1700
Data Index: 8201346 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.4696. Min Act: -0.1700
Data Index: 8448233 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.4696. Min Act: -0.1700
Data Index: 6274441 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.4383. Min Act: -0.1700
Data Index: 2317540 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.4383. Min Act: -0.1700
Data Index: 4491807 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.4071. Min Act: -0.1700
Data Index: 8000476 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.3758. Min Act: -0.1700
Data Index: 8075833 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.4071. Min Act: -0.1700
Data Index: 7498205 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.3133. Min Act: -0.1700
Data Index: 1727878 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.3133. Min Act: -0.1700
Data Index: 2362354 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.2821. Min Act: -0.1700
Data Index: 1019344 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.2821. Min Act: -0.1700
Data Index: 1038681 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.2821. Min Act: -0.1700
Data Index: 2478408 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.2821. Min Act: -0.1700
Data Index: 4782662 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.2821. Min Act: -0.1700
Data Index: 4343690 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0946. Min Range: -7.0946
Max Act: 6.2821. Min Act: -0.1700
Data Index: 1211540 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19