Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4426 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0981. Min Range: -5.0981
Max Act: 5.0981. Min Act: -0.1700
Data Index: 2844135 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0981. Min Range: -5.0981
Max Act: 5.0981. Min Act: -0.1700
Data Index: 1804179 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0981. Min Range: -5.0981
Max Act: 5.0356. Min Act: -0.1700
Data Index: 6220541 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0981. Min Range: -5.0981
Max Act: 5.0356. Min Act: -0.1700
Data Index: 3713014 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0981. Min Range: -5.0981
Max Act: 5.0668. Min Act: -0.1700
Data Index: 6250265 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0981. Min Range: -5.0981
Max Act: 5.0043. Min Act: -0.1700
Data Index: 6795761 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0981. Min Range: -5.0981
Max Act: 4.9731. Min Act: -0.1700
Data Index: 7343583 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0981. Min Range: -5.0981
Max Act: 4.9731. Min Act: -0.1700
Data Index: 2621326 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0981. Min Range: -5.0981
Max Act: 4.9731. Min Act: -0.1700
Data Index: 4583295 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0981. Min Range: -5.0981
Max Act: 5.0043. Min Act: -0.1700
Data Index: 6428451 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0981. Min Range: -5.0981
Max Act: 4.9731. Min Act: -0.1700
Data Index: 7787149 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0981. Min Range: -5.0981
Max Act: 4.9106. Min Act: -0.1700
Data Index: 8142945 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0981. Min Range: -5.0981
Max Act: 4.9106. Min Act: -0.1700
Data Index: 7484840 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0981. Min Range: -5.0981
Max Act: 4.9106. Min Act: -0.1700
Data Index: 2920368 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0981. Min Range: -5.0981
Max Act: 4.9106. Min Act: -0.1700
Data Index: 8524712 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0981. Min Range: -5.0981
Max Act: 4.8793. Min Act: -0.1700
Data Index: 5492821 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0981. Min Range: -5.0981
Max Act: 4.8793. Min Act: -0.1700
Data Index: 5513940 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0981. Min Range: -5.0981
Max Act: 4.8793. Min Act: -0.1700
Data Index: 2856331 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0981. Min Range: -5.0981
Max Act: 4.8793. Min Act: -0.1700
Data Index: 3673866 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0981. Min Range: -5.0981
Max Act: 4.8793. Min Act: -0.1700
Data Index: 6106644 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19