Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 922 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0300. Min Range: -6.0300
Max Act: 6.0300. Min Act: -0.1700
Data Index: 7856700 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.9675. Min Act: -0.1700
Data Index: 3720468 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.9050. Min Act: -0.1700
Data Index: 126249 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.8425. Min Act: -0.1700
Data Index: 789056 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.9050. Min Act: -0.1700
Data Index: 4488607 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.8425. Min Act: -0.1700
Data Index: 1127576 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7800. Min Act: -0.1700
Data Index: 1807217 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7800. Min Act: -0.1700
Data Index: 4725977 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7800. Min Act: -0.1700
Data Index: 5041588 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7800. Min Act: -0.1700
Data Index: 4215614 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7487. Min Act: -0.1700
Data Index: 7624091 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7175. Min Act: -0.1700
Data Index: 6006010 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7175. Min Act: -0.1700
Data Index: 3826410 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7175. Min Act: -0.1700
Data Index: 3353003 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7175. Min Act: -0.1700
Data Index: 658584 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.6862. Min Act: -0.1700
Data Index: 13662 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.6550. Min Act: -0.1700
Data Index: 2831546 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.6550. Min Act: -0.1700
Data Index: 4973143 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.6550. Min Act: -0.1700
Data Index: 271710 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.6550. Min Act: -0.1700
Data Index: 1322630 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19