Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2706 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.3327. Min Act: -0.1700
Data Index: 3410997 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.2390. Min Act: -0.1700
Data Index: 7669565 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.2077. Min Act: -0.1700
Data Index: 4125701 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.2077. Min Act: -0.1700
Data Index: 6943476 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.1765. Min Act: -0.1700
Data Index: 175536 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.1765. Min Act: -0.1700
Data Index: 8261801 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.1452. Min Act: -0.1700
Data Index: 4366918 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.1452. Min Act: -0.1700
Data Index: 6558584 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.1452. Min Act: -0.1700
Data Index: 8626805 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.1452. Min Act: -0.1700
Data Index: 8213995 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.1452. Min Act: -0.1700
Data Index: 2369146 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.1140. Min Act: -0.1700
Data Index: 2578492 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.1140. Min Act: -0.1700
Data Index: 3379770 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.0827. Min Act: -0.1700
Data Index: 2471677 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.0827. Min Act: -0.1700
Data Index: 7266384 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.0515. Min Act: -0.1700
Data Index: 170902 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.0515. Min Act: -0.1700
Data Index: 4676349 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.0515. Min Act: -0.1700
Data Index: 6564676 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.0202. Min Act: -0.1700
Data Index: 2046486 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3327. Min Range: -6.3327
Max Act: 6.0202. Min Act: -0.1700
Data Index: 7228448 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19