Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1528 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.7970. Min Act: -0.1700
Data Index: 4870027 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.7033. Min Act: -0.1700
Data Index: 3204009 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.7033. Min Act: -0.1700
Data Index: 920731 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.6408. Min Act: -0.1700
Data Index: 7609512 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.5783. Min Act: -0.1700
Data Index: 3521973 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.5470. Min Act: -0.1700
Data Index: 6318602 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.4845. Min Act: -0.1700
Data Index: 3974453 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.4533. Min Act: -0.1700
Data Index: 8367514 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.4220. Min Act: -0.1700
Data Index: 3070486 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.3908. Min Act: -0.1700
Data Index: 2830602 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.3908. Min Act: -0.1700
Data Index: 4362850 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.3283. Min Act: -0.1700
Data Index: 1250799 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.3595. Min Act: -0.1700
Data Index: 718157 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.3595. Min Act: -0.1700
Data Index: 3135450 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.3595. Min Act: -0.1700
Data Index: 371338 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.3283. Min Act: -0.1700
Data Index: 7612450 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.3595. Min Act: -0.1700
Data Index: 601763 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.2970. Min Act: -0.1700
Data Index: 2111249 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.2970. Min Act: -0.1700
Data Index: 1846480 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7970. Min Range: -5.7970
Max Act: 5.2970. Min Act: -0.1700
Data Index: 332197 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19