Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3959 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.4223. Min Act: -0.1700
Data Index: 5330102 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.3286. Min Act: -0.1700
Data Index: 5724115 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.2973. Min Act: -0.1700
Data Index: 8408883 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.1098. Min Act: -0.1700
Data Index: 7857266 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.1098. Min Act: -0.1700
Data Index: 1586150 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.0786. Min Act: -0.1700
Data Index: 4677599 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.0786. Min Act: -0.1700
Data Index: 8070157 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.0786. Min Act: -0.1700
Data Index: 372888 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.0786. Min Act: -0.1700
Data Index: 5504326 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.0786. Min Act: -0.1700
Data Index: 4196514 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.0786. Min Act: -0.1700
Data Index: 3500365 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.0473. Min Act: -0.1700
Data Index: 3461041 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.0473. Min Act: -0.1700
Data Index: 1272146 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.0473. Min Act: -0.1700
Data Index: 5162460 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.0161. Min Act: -0.1700
Data Index: 6525261 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4223. Min Range: -5.4223
Max Act: 5.0161. Min Act: -0.1700
Data Index: 3217360 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4223. Min Range: -5.4223
Max Act: 4.9848. Min Act: -0.1700
Data Index: 971806 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4223. Min Range: -5.4223
Max Act: 4.9848. Min Act: -0.1700
Data Index: 1229169 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4223. Min Range: -5.4223
Max Act: 4.9848. Min Act: -0.1700
Data Index: 7586629 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4223. Min Range: -5.4223
Max Act: 4.9848. Min Act: -0.1700
Data Index: 5271916 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19