Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2881 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.4080. Min Act: -0.1700
Data Index: 7597685 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.3766. Min Act: -0.1700
Data Index: 3473888 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.3609. Min Act: -0.1700
Data Index: 1609584 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.2824. Min Act: -0.1700
Data Index: 4386580 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.2667. Min Act: -0.1700
Data Index: 461468 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.2667. Min Act: -0.1700
Data Index: 1457461 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.2510. Min Act: -0.1700
Data Index: 1498500 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.2039. Min Act: -0.1700
Data Index: 3888521 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.2196. Min Act: -0.1700
Data Index: 7437265 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.1881. Min Act: -0.1700
Data Index: 1162271 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.2039. Min Act: -0.1700
Data Index: 4953615 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.2039. Min Act: -0.1700
Data Index: 2202125 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.1881. Min Act: -0.1700
Data Index: 5445216 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.1881. Min Act: -0.1700
Data Index: 8547358 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.1881. Min Act: -0.1700
Data Index: 3895019 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.1881. Min Act: -0.1700
Data Index: 1973478 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.1881. Min Act: -0.1700
Data Index: 4260683 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.1724. Min Act: -0.1700
Data Index: 4847427 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.1409. Min Act: -0.1700
Data Index: 3110336 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4080. Min Range: -3.4080
Max Act: 3.1567. Min Act: -0.1700
Data Index: 4207888 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19