Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1424 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2574. Min Range: -5.2574
Max Act: 5.2574. Min Act: -0.1700
Data Index: 21520 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2574. Min Range: -5.2574
Max Act: 5.2574. Min Act: -0.1700
Data Index: 3907591 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2574. Min Range: -5.2574
Max Act: 5.2574. Min Act: -0.1700
Data Index: 3742394 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2574. Min Range: -5.2574
Max Act: 5.1949. Min Act: -0.1700
Data Index: 3543793 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2574. Min Range: -5.2574
Max Act: 5.1636. Min Act: -0.1700
Data Index: 7091919 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2574. Min Range: -5.2574
Max Act: 5.1324. Min Act: -0.1700
Data Index: 3171936 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2574. Min Range: -5.2574
Max Act: 5.1011. Min Act: -0.1700
Data Index: 8373207 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2574. Min Range: -5.2574
Max Act: 5.1011. Min Act: -0.1700
Data Index: 2387845 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2574. Min Range: -5.2574
Max Act: 5.1011. Min Act: -0.1700
Data Index: 1480573 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2574. Min Range: -5.2574
Max Act: 5.0386. Min Act: -0.1700
Data Index: 8300254 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2574. Min Range: -5.2574
Max Act: 5.0074. Min Act: -0.1700
Data Index: 1525732 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2574. Min Range: -5.2574
Max Act: 4.9761. Min Act: -0.1700
Data Index: 4992254 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2574. Min Range: -5.2574
Max Act: 5.0074. Min Act: -0.1700
Data Index: 5170373 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2574. Min Range: -5.2574
Max Act: 4.9761. Min Act: -0.1700
Data Index: 6805868 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2574. Min Range: -5.2574
Max Act: 4.9761. Min Act: -0.1700
Data Index: 7035595 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2574. Min Range: -5.2574
Max Act: 4.9761. Min Act: -0.1700
Data Index: 3304518 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2574. Min Range: -5.2574
Max Act: 4.9761. Min Act: -0.1700
Data Index: 7712663 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2574. Min Range: -5.2574
Max Act: 4.9761. Min Act: -0.1700
Data Index: 6411081 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2574. Min Range: -5.2574
Max Act: 4.9449. Min Act: -0.1700
Data Index: 1798476 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2574. Min Range: -5.2574
Max Act: 4.9761. Min Act: -0.1700
Data Index: 5238463 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19