Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1334 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.6876. Min Act: -0.1700
Data Index: 2512200 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.3439. Min Act: -0.1700
Data Index: 4142383 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.3439. Min Act: -0.1700
Data Index: 1859259 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.3439. Min Act: -0.1700
Data Index: 3869431 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.3126. Min Act: -0.1700
Data Index: 1358385 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.2814. Min Act: -0.1700
Data Index: 4142388 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.2189. Min Act: -0.1700
Data Index: 4142386 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.2189. Min Act: -0.1700
Data Index: 7636832 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.1876. Min Act: -0.1700
Data Index: 8457085 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.1876. Min Act: -0.1700
Data Index: 4097496 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.1564. Min Act: -0.1700
Data Index: 1725498 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.1564. Min Act: -0.1700
Data Index: 1774320 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.1564. Min Act: -0.1700
Data Index: 3342868 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.1564. Min Act: -0.1700
Data Index: 8088394 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.1876. Min Act: -0.1700
Data Index: 2537352 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.1564. Min Act: -0.1700
Data Index: 509472 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.1876. Min Act: -0.1700
Data Index: 1725499 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.1251. Min Act: -0.1700
Data Index: 6000051 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.1251. Min Act: -0.1700
Data Index: 5627453 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6876. Min Range: -6.6876
Max Act: 6.1251. Min Act: -0.1700
Data Index: 3359665 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19