Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3185 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3031. Min Range: -5.3031
Max Act: 5.3031. Min Act: -0.1700
Data Index: 67978 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3031. Min Range: -5.3031
Max Act: 5.2718. Min Act: -0.1700
Data Index: 1024027 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3031. Min Range: -5.3031
Max Act: 5.2093. Min Act: -0.1700
Data Index: 885488 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3031. Min Range: -5.3031
Max Act: 5.1781. Min Act: -0.1700
Data Index: 122969 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3031. Min Range: -5.3031
Max Act: 5.1468. Min Act: -0.1700
Data Index: 1929053 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3031. Min Range: -5.3031
Max Act: 5.1156. Min Act: -0.1700
Data Index: 8402532 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3031. Min Range: -5.3031
Max Act: 5.1156. Min Act: -0.1700
Data Index: 8519680 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3031. Min Range: -5.3031
Max Act: 5.0531. Min Act: -0.1700
Data Index: 2435987 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3031. Min Range: -5.3031
Max Act: 5.0218. Min Act: -0.1700
Data Index: 2620731 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3031. Min Range: -5.3031
Max Act: 5.0218. Min Act: -0.1700
Data Index: 2935098 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3031. Min Range: -5.3031
Max Act: 5.0218. Min Act: -0.1700
Data Index: 1417600 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3031. Min Range: -5.3031
Max Act: 4.9906. Min Act: -0.1700
Data Index: 6491929 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3031. Min Range: -5.3031
Max Act: 4.9906. Min Act: -0.1700
Data Index: 3115558 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3031. Min Range: -5.3031
Max Act: 4.9906. Min Act: -0.1700
Data Index: 5954112 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3031. Min Range: -5.3031
Max Act: 4.9906. Min Act: -0.1700
Data Index: 788247 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3031. Min Range: -5.3031
Max Act: 4.9593. Min Act: -0.1700
Data Index: 8198331 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3031. Min Range: -5.3031
Max Act: 4.9593. Min Act: -0.1700
Data Index: 966916 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3031. Min Range: -5.3031
Max Act: 4.9593. Min Act: -0.1700
Data Index: 5524853 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3031. Min Range: -5.3031
Max Act: 4.9593. Min Act: -0.1700
Data Index: 1183385 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3031. Min Range: -5.3031
Max Act: 4.9593. Min Act: -0.1700
Data Index: 3335295 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19