Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0377. Min Range: -4.0377
Max Act: 4.0377. Min Act: -0.1700
Data Index: 1569913 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0377. Min Range: -4.0377
Max Act: 4.0065. Min Act: -0.1700
Data Index: 2702305 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.9752. Min Act: -0.1700
Data Index: 3851076 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.9440. Min Act: -0.1700
Data Index: 4737521 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.9440. Min Act: -0.1700
Data Index: 8244690 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.8814. Min Act: -0.1700
Data Index: 8819871 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.9127. Min Act: -0.1700
Data Index: 7759477 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.9127. Min Act: -0.1700
Data Index: 6905335 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.9127. Min Act: -0.1700
Data Index: 370072 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.8814. Min Act: -0.1700
Data Index: 2728038 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.8814. Min Act: -0.1700
Data Index: 4081674 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.8814. Min Act: -0.1700
Data Index: 1135367 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.8502. Min Act: -0.1700
Data Index: 3566577 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.8502. Min Act: -0.1700
Data Index: 165203 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.8502. Min Act: -0.1700
Data Index: 5962619 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.8814. Min Act: -0.1700
Data Index: 2766346 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.8502. Min Act: -0.1700
Data Index: 20239 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.8189. Min Act: -0.1700
Data Index: 5882122 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.8189. Min Act: -0.1700
Data Index: 385014 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0377. Min Range: -4.0377
Max Act: 3.7876. Min Act: -0.1700
Data Index: 196774 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19