Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2019 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4167. Min Range: -6.4167
Max Act: 6.4167. Min Act: -0.1700
Data Index: 776122 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4167. Min Range: -6.4167
Max Act: 6.2917. Min Act: -0.1700
Data Index: 7188441 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4167. Min Range: -6.4167
Max Act: 6.1980. Min Act: -0.1700
Data Index: 1335221 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4167. Min Range: -6.4167
Max Act: 6.1355. Min Act: -0.1700
Data Index: 5132906 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4167. Min Range: -6.4167
Max Act: 6.0105. Min Act: -0.1700
Data Index: 4832940 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.9792. Min Act: -0.1700
Data Index: 2860818 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.9792. Min Act: -0.1700
Data Index: 1162647 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.9792. Min Act: -0.1700
Data Index: 5793228 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.9480. Min Act: -0.1700
Data Index: 5107512 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.9480. Min Act: -0.1700
Data Index: 2925920 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.9480. Min Act: -0.1700
Data Index: 7927711 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.8855. Min Act: -0.1700
Data Index: 7555577 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.9167. Min Act: -0.1700
Data Index: 2520727 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.9167. Min Act: -0.1700
Data Index: 1885320 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.8542. Min Act: -0.1700
Data Index: 4005668 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.8542. Min Act: -0.1700
Data Index: 2710224 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.8542. Min Act: -0.1700
Data Index: 5617131 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.8230. Min Act: -0.1700
Data Index: 5543980 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.8230. Min Act: -0.1700
Data Index: 3684363 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4167. Min Range: -6.4167
Max Act: 5.8230. Min Act: -0.1700
Data Index: 3732559 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19