Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1512 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.2478. Min Act: -0.1700
Data Index: 3390555 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.2166. Min Act: -0.1700
Data Index: 7730739 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.2166. Min Act: -0.1700
Data Index: 3203920 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.2166. Min Act: -0.1700
Data Index: 1081803 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1853. Min Act: -0.1700
Data Index: 1609068 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1853. Min Act: -0.1700
Data Index: 989528 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1853. Min Act: -0.1700
Data Index: 3489019 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1853. Min Act: -0.1700
Data Index: 5451571 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1541. Min Act: -0.1700
Data Index: 1186405 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1541. Min Act: -0.1700
Data Index: 908980 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1541. Min Act: -0.1700
Data Index: 7607268 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1541. Min Act: -0.1700
Data Index: 4649112 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1541. Min Act: -0.1700
Data Index: 4643151 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1541. Min Act: -0.1700
Data Index: 4565119 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1541. Min Act: -0.1700
Data Index: 1843006 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1541. Min Act: -0.1700
Data Index: 4335208 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1541. Min Act: -0.1700
Data Index: 710248 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1541. Min Act: -0.1700
Data Index: 690697 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1541. Min Act: -0.1700
Data Index: 3875153 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2478. Min Range: -4.2478
Max Act: 4.1541. Min Act: -0.1700
Data Index: 1740403 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19