Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3853 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.7647. Min Act: -0.1700
Data Index: 3467691 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.7647. Min Act: -0.1700
Data Index: 7041829 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.7335. Min Act: -0.1700
Data Index: 5131331 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.7022. Min Act: -0.1700
Data Index: 5536878 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.6085. Min Act: -0.1700
Data Index: 217454 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.6085. Min Act: -0.1700
Data Index: 3149511 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.5460. Min Act: -0.1700
Data Index: 5901864 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.5147. Min Act: -0.1700
Data Index: 3346568 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.5147. Min Act: -0.1700
Data Index: 4603834 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.5147. Min Act: -0.1700
Data Index: 8137097 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.4522. Min Act: -0.1700
Data Index: 1157940 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.4835. Min Act: -0.1700
Data Index: 5197490 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.4835. Min Act: -0.1700
Data Index: 5372530 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.4835. Min Act: -0.1700
Data Index: 4620422 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.4522. Min Act: -0.1700
Data Index: 4345125 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.4210. Min Act: -0.1700
Data Index: 7535119 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.3897. Min Act: -0.1700
Data Index: 1439830 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.4210. Min Act: -0.1700
Data Index: 6896762 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.3897. Min Act: -0.1700
Data Index: 2936176 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7647. Min Range: -5.7647
Max Act: 5.3897. Min Act: -0.1700
Data Index: 5859631 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19