Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3305. Min Range: -3.3305
Max Act: 3.3305. Min Act: -0.1700
Data Index: 1431334 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3305. Min Range: -3.3305
Max Act: 3.0947. Min Act: -0.1700
Data Index: 6077865 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3305. Min Range: -3.3305
Max Act: 3.0158. Min Act: -0.1700
Data Index: 6165713 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.9684. Min Act: -0.1700
Data Index: 5214840 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.9050. Min Act: -0.1700
Data Index: 6086706 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.9050. Min Act: -0.1700
Data Index: 7742366 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.8733. Min Act: -0.1700
Data Index: 2680762 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.8733. Min Act: -0.1700
Data Index: 1177282 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.8256. Min Act: -0.1700
Data Index: 8699601 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.8574. Min Act: -0.1700
Data Index: 4481916 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.8256. Min Act: -0.1700
Data Index: 4481909 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.8256. Min Act: -0.1700
Data Index: 2745476 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.8415. Min Act: -0.1700
Data Index: 2469083 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.8097. Min Act: -0.1700
Data Index: 4586739 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.7938. Min Act: -0.1700
Data Index: 6124052 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.7938. Min Act: -0.1700
Data Index: 3040089 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.7778. Min Act: -0.1700
Data Index: 310152 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.7778. Min Act: -0.1700
Data Index: 3543322 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.7619. Min Act: -0.1700
Data Index: 5959386 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3305. Min Range: -3.3305
Max Act: 2.7778. Min Act: -0.1700
Data Index: 5149376 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19