Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6237 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.7537. Min Act: -0.1700
Data Index: 3214768 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.6599. Min Act: -0.1700
Data Index: 8152420 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.6599. Min Act: -0.1700
Data Index: 378359 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.5349. Min Act: -0.1700
Data Index: 7741987 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.5662. Min Act: -0.1700
Data Index: 2500470 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.4724. Min Act: -0.1700
Data Index: 3106587 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.4724. Min Act: -0.1700
Data Index: 7085365 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.5037. Min Act: -0.1700
Data Index: 6862941 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.4412. Min Act: -0.1700
Data Index: 2056975 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.4412. Min Act: -0.1700
Data Index: 69493 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.3474. Min Act: -0.1700
Data Index: 4286514 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.4099. Min Act: -0.1700
Data Index: 2603246 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.3162. Min Act: -0.1700
Data Index: 2329797 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.3474. Min Act: -0.1700
Data Index: 8262571 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.3162. Min Act: -0.1700
Data Index: 4754027 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.2849. Min Act: -0.1700
Data Index: 3192818 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.3162. Min Act: -0.1700
Data Index: 589109 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.3162. Min Act: -0.1700
Data Index: 7514458 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.3162. Min Act: -0.1700
Data Index: 1249077 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.3162. Min Act: -0.1700
Data Index: 2135497 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19