Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3772 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.8535. Min Act: -0.1700
Data Index: 7662040 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.8535. Min Act: -0.1700
Data Index: 8795948 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.8217. Min Act: -0.1700
Data Index: 3876408 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.8058. Min Act: -0.1700
Data Index: 4635738 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.8058. Min Act: -0.1700
Data Index: 4635737 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.7899. Min Act: -0.1700
Data Index: 7229575 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.7740. Min Act: -0.1700
Data Index: 7467272 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.7740. Min Act: -0.1700
Data Index: 8784915 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.7580. Min Act: -0.1700
Data Index: 3049703 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.7420. Min Act: -0.1700
Data Index: 2005554 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.7420. Min Act: -0.1700
Data Index: 8548044 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.6941. Min Act: -0.1700
Data Index: 6189257 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.7101. Min Act: -0.1700
Data Index: 7678063 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.6941. Min Act: -0.1700
Data Index: 8722064 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.6941. Min Act: -0.1700
Data Index: 7565343 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.6941. Min Act: -0.1700
Data Index: 8318730 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.6781. Min Act: -0.1700
Data Index: 4420461 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.6781. Min Act: -0.1700
Data Index: 8362191 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.6620. Min Act: -0.1700
Data Index: 148095 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8535. Min Range: -2.8535
Max Act: 2.6620. Min Act: -0.1700
Data Index: 180272 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19