Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2490 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.2383. Min Act: -0.1700
Data Index: 8122079 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.1911. Min Act: -0.1700
Data Index: 4184751 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.1282. Min Act: -0.1700
Data Index: 4874311 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.1124. Min Act: -0.1700
Data Index: 230240 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.0967. Min Act: -0.1700
Data Index: 483939 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.1124. Min Act: -0.1700
Data Index: 2299842 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.0967. Min Act: -0.1700
Data Index: 8034797 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.0651. Min Act: -0.1700
Data Index: 3441219 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.0494. Min Act: -0.1700
Data Index: 1782778 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.0336. Min Act: -0.1700
Data Index: 6730182 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.0336. Min Act: -0.1700
Data Index: 2021553 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.0020. Min Act: -0.1700
Data Index: 2449115 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.0020. Min Act: -0.1700
Data Index: 7801909 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2383. Min Range: -3.2383
Max Act: 3.0020. Min Act: -0.1700
Data Index: 7501381 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2383. Min Range: -3.2383
Max Act: 2.9862. Min Act: -0.1700
Data Index: 2694623 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2383. Min Range: -3.2383
Max Act: 2.9387. Min Act: -0.1700
Data Index: 6424151 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2383. Min Range: -3.2383
Max Act: 2.9545. Min Act: -0.1700
Data Index: 5015823 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2383. Min Range: -3.2383
Max Act: 2.9387. Min Act: -0.1700
Data Index: 7034604 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2383. Min Range: -3.2383
Max Act: 2.9387. Min Act: -0.1700
Data Index: 6190873 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2383. Min Range: -3.2383
Max Act: 2.9229. Min Act: -0.1700
Data Index: 2746120 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19