Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3939 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4327. Min Range: -8.4327
Max Act: 8.4327. Min Act: -0.1700
Data Index: 919307 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4327. Min Range: -8.4327
Max Act: 8.3077. Min Act: -0.1700
Data Index: 4158711 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4327. Min Range: -8.4327
Max Act: 8.1827. Min Act: -0.1700
Data Index: 5633443 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4327. Min Range: -8.4327
Max Act: 8.3077. Min Act: -0.1700
Data Index: 2918933 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4327. Min Range: -8.4327
Max Act: 8.1827. Min Act: -0.1700
Data Index: 8123525 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4327. Min Range: -8.4327
Max Act: 8.1202. Min Act: -0.1700
Data Index: 1014963 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4327. Min Range: -8.4327
Max Act: 8.0577. Min Act: -0.1700
Data Index: 4593223 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4327. Min Range: -8.4327
Max Act: 8.0577. Min Act: -0.1700
Data Index: 3176218 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4327. Min Range: -8.4327
Max Act: 8.1202. Min Act: -0.1700
Data Index: 3600083 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4327. Min Range: -8.4327
Max Act: 8.0577. Min Act: -0.1700
Data Index: 1797968 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4327. Min Range: -8.4327
Max Act: 8.0577. Min Act: -0.1700
Data Index: 6292350 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4327. Min Range: -8.4327
Max Act: 8.0264. Min Act: -0.1700
Data Index: 3614467 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4327. Min Range: -8.4327
Max Act: 8.0264. Min Act: -0.1700
Data Index: 2217382 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4327. Min Range: -8.4327
Max Act: 7.9639. Min Act: -0.1700
Data Index: 2284148 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4327. Min Range: -8.4327
Max Act: 7.9639. Min Act: -0.1700
Data Index: 8404085 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4327. Min Range: -8.4327
Max Act: 7.9327. Min Act: -0.1700
Data Index: 662568 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4327. Min Range: -8.4327
Max Act: 7.9327. Min Act: -0.1700
Data Index: 7636914 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4327. Min Range: -8.4327
Max Act: 7.9327. Min Act: -0.1700
Data Index: 6586328 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4327. Min Range: -8.4327
Max Act: 7.9327. Min Act: -0.1700
Data Index: 5324230 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4327. Min Range: -8.4327
Max Act: 7.9014. Min Act: -0.1700
Data Index: 2280197 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19