Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2236 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0761. Min Range: -5.0761
Max Act: 5.0761. Min Act: -0.1700
Data Index: 6286587 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0761. Min Range: -5.0761
Max Act: 5.0449. Min Act: -0.1700
Data Index: 1188339 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0761. Min Range: -5.0761
Max Act: 5.0449. Min Act: -0.1700
Data Index: 8773635 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.8886. Min Act: -0.1700
Data Index: 1046570 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.8886. Min Act: -0.1700
Data Index: 7448605 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.8886. Min Act: -0.1700
Data Index: 613724 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.8574. Min Act: -0.1700
Data Index: 4780132 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.8574. Min Act: -0.1700
Data Index: 3065966 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.7949. Min Act: -0.1700
Data Index: 6725919 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.7949. Min Act: -0.1700
Data Index: 4587071 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.7949. Min Act: -0.1700
Data Index: 7418335 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.7949. Min Act: -0.1700
Data Index: 5507025 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.7636. Min Act: -0.1700
Data Index: 472393 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.7636. Min Act: -0.1700
Data Index: 6056099 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.7011. Min Act: -0.1700
Data Index: 4655314 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.7324. Min Act: -0.1700
Data Index: 305485 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.6699. Min Act: -0.1700
Data Index: 497983 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.6699. Min Act: -0.1700
Data Index: 6765826 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.7011. Min Act: -0.1700
Data Index: 911812 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0761. Min Range: -5.0761
Max Act: 4.7324. Min Act: -0.1700
Data Index: 2636240 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19