Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1865. Min Range: -6.1865
Max Act: 6.1865. Min Act: -0.1700
Data Index: 2318323 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1865. Min Range: -6.1865
Max Act: 6.0928. Min Act: -0.1700
Data Index: 4042757 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.9678. Min Act: -0.1700
Data Index: 980700 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.9365. Min Act: -0.1700
Data Index: 3207196 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.9053. Min Act: -0.1700
Data Index: 246441 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.9053. Min Act: -0.1700
Data Index: 2402740 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.8428. Min Act: -0.1700
Data Index: 2658581 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.7803. Min Act: -0.1700
Data Index: 8708526 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.7803. Min Act: -0.1700
Data Index: 7860037 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.7490. Min Act: -0.1700
Data Index: 4609623 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.7178. Min Act: -0.1700
Data Index: 7085671 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.7178. Min Act: -0.1700
Data Index: 7053968 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.7178. Min Act: -0.1700
Data Index: 4266255 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.6865. Min Act: -0.1700
Data Index: 4743282 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.6553. Min Act: -0.1700
Data Index: 7935393 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.6240. Min Act: -0.1700
Data Index: 722939 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.6240. Min Act: -0.1700
Data Index: 4743283 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.6240. Min Act: -0.1700
Data Index: 4658950 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.6240. Min Act: -0.1700
Data Index: 6803 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1865. Min Range: -6.1865
Max Act: 5.6240. Min Act: -0.1700
Data Index: 3224256 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19