Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1475 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.8246. Min Act: -0.1700
Data Index: 5574721 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.7933. Min Act: -0.1700
Data Index: 8237704 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.6996. Min Act: -0.1700
Data Index: 661156 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.6371. Min Act: -0.1700
Data Index: 3445460 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.6371. Min Act: -0.1700
Data Index: 4192147 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.6371. Min Act: -0.1700
Data Index: 3788455 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.6058. Min Act: -0.1700
Data Index: 5428930 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.6058. Min Act: -0.1700
Data Index: 7031578 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.6058. Min Act: -0.1700
Data Index: 6126972 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.5433. Min Act: -0.1700
Data Index: 7556451 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.5433. Min Act: -0.1700
Data Index: 2844782 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.5121. Min Act: -0.1700
Data Index: 7643633 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.5433. Min Act: -0.1700
Data Index: 8478314 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.5121. Min Act: -0.1700
Data Index: 4108612 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.5121. Min Act: -0.1700
Data Index: 4653705 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.5121. Min Act: -0.1700
Data Index: 1973294 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.5121. Min Act: -0.1700
Data Index: 6185881 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.4808. Min Act: -0.1700
Data Index: 4906827 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.4808. Min Act: -0.1700
Data Index: 808225 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8246. Min Range: -4.8246
Max Act: 4.4808. Min Act: -0.1700
Data Index: 1763212 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19