Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1850 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4522. Min Range: -8.4522
Max Act: 8.4522. Min Act: -0.1700
Data Index: 4045617 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.7960. Min Act: -0.1700
Data Index: 3931018 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.7022. Min Act: -0.1700
Data Index: 5549254 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.7022. Min Act: -0.1700
Data Index: 1801417 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.6085. Min Act: -0.1700
Data Index: 8661574 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.6397. Min Act: -0.1700
Data Index: 3575446 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.6397. Min Act: -0.1700
Data Index: 5395072 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.6397. Min Act: -0.1700
Data Index: 5452134 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.5772. Min Act: -0.1700
Data Index: 1357742 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.5460. Min Act: -0.1700
Data Index: 7022254 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.5772. Min Act: -0.1700
Data Index: 6943951 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.5772. Min Act: -0.1700
Data Index: 2206253 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.5147. Min Act: -0.1700
Data Index: 5871725 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.4835. Min Act: -0.1700
Data Index: 2987750 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.4522. Min Act: -0.1700
Data Index: 356306 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.4522. Min Act: -0.1700
Data Index: 6506717 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.4210. Min Act: -0.1700
Data Index: 7490882 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.4210. Min Act: -0.1700
Data Index: 1798548 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.3897. Min Act: -0.1700
Data Index: 1246398 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4522. Min Range: -8.4522
Max Act: 7.3897. Min Act: -0.1700
Data Index: 3080691 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19