Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6222 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.6275. Min Act: -0.1700
Data Index: 7265606 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.5963. Min Act: -0.1700
Data Index: 6667808 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.5963. Min Act: -0.1700
Data Index: 4759518 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.5338. Min Act: -0.1700
Data Index: 6367731 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.5025. Min Act: -0.1700
Data Index: 3181945 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4713. Min Act: -0.1700
Data Index: 2134503 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3775. Min Act: -0.1700
Data Index: 7827293 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4088. Min Act: -0.1700
Data Index: 222167 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4088. Min Act: -0.1700
Data Index: 8192071 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3775. Min Act: -0.1700
Data Index: 5992662 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3775. Min Act: -0.1700
Data Index: 1030619 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3775. Min Act: -0.1700
Data Index: 1194989 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3463. Min Act: -0.1700
Data Index: 8634034 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3150. Min Act: -0.1700
Data Index: 588690 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3463. Min Act: -0.1700
Data Index: 7880297 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3150. Min Act: -0.1700
Data Index: 1621870 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.2838. Min Act: -0.1700
Data Index: 1720533 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3150. Min Act: -0.1700
Data Index: 4574295 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3150. Min Act: -0.1700
Data Index: 7042245 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.2838. Min Act: -0.1700
Data Index: 6644795 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19