Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2761 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6385. Min Range: -9.6385
Max Act: 9.6385. Min Act: -0.1700
Data Index: 804385 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6385. Min Range: -9.6385
Max Act: 9.3885. Min Act: -0.1700
Data Index: 493352 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6385. Min Range: -9.6385
Max Act: 9.2635. Min Act: -0.1700
Data Index: 1636162 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6385. Min Range: -9.6385
Max Act: 9.1385. Min Act: -0.1700
Data Index: 7522317 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6385. Min Range: -9.6385
Max Act: 9.1385. Min Act: -0.1700
Data Index: 356078 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6385. Min Range: -9.6385
Max Act: 9.1385. Min Act: -0.1700
Data Index: 728274 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6385. Min Range: -9.6385
Max Act: 9.1385. Min Act: -0.1700
Data Index: 4608117 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6385. Min Range: -9.6385
Max Act: 9.0135. Min Act: -0.1700
Data Index: 6427623 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6385. Min Range: -9.6385
Max Act: 9.0135. Min Act: -0.1700
Data Index: 1812320 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6385. Min Range: -9.6385
Max Act: 8.9510. Min Act: -0.1700
Data Index: 3792485 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6385. Min Range: -9.6385
Max Act: 8.8885. Min Act: -0.1700
Data Index: 2622886 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6385. Min Range: -9.6385
Max Act: 8.8885. Min Act: -0.1700
Data Index: 1251858 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6385. Min Range: -9.6385
Max Act: 8.8885. Min Act: -0.1700
Data Index: 4772121 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6385. Min Range: -9.6385
Max Act: 8.8260. Min Act: -0.1700
Data Index: 8695525 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6385. Min Range: -9.6385
Max Act: 8.8260. Min Act: -0.1700
Data Index: 7751819 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6385. Min Range: -9.6385
Max Act: 8.7010. Min Act: -0.1700
Data Index: 8130877 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6385. Min Range: -9.6385
Max Act: 8.7010. Min Act: -0.1700
Data Index: 4169385 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6385. Min Range: -9.6385
Max Act: 8.7010. Min Act: -0.1700
Data Index: 3465548 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6385. Min Range: -9.6385
Max Act: 8.6385. Min Act: -0.1700
Data Index: 3917367 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6385. Min Range: -9.6385
Max Act: 8.6385. Min Act: -0.1700
Data Index: 127840 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19