Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5031 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.9077. Min Act: -0.1700
Data Index: 7696262 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.9389. Min Act: -0.1700
Data Index: 3297066 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.8764. Min Act: -0.1700
Data Index: 7449167 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.8451. Min Act: -0.1700
Data Index: 1329578 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.7826. Min Act: -0.1700
Data Index: 1797117 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.7670. Min Act: -0.1700
Data Index: 5418215 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.7357. Min Act: -0.1700
Data Index: 3134570 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.7200. Min Act: -0.1700
Data Index: 7899928 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.7044. Min Act: -0.1700
Data Index: 8453609 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.6887. Min Act: -0.1700
Data Index: 4080385 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.6887. Min Act: -0.1700
Data Index: 300386 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.6887. Min Act: -0.1700
Data Index: 8313690 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.6887. Min Act: -0.1700
Data Index: 5955193 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.6575. Min Act: -0.1700
Data Index: 5174979 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.6575. Min Act: -0.1700
Data Index: 2735502 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.6418. Min Act: -0.1700
Data Index: 2343406 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.6262. Min Act: -0.1700
Data Index: 5742805 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.6105. Min Act: -0.1700
Data Index: 7074022 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.6262. Min Act: -0.1700
Data Index: 233534 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9389. Min Range: -3.9389
Max Act: 3.6262. Min Act: -0.1700
Data Index: 5657014 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19