Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1237. Min Range: -6.1237
Max Act: 6.1237. Min Act: -0.1700
Data Index: 3386027 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.9675. Min Act: -0.1700
Data Index: 3588792 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.9362. Min Act: -0.1700
Data Index: 2180775 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.7800. Min Act: -0.1700
Data Index: 7820800 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.7487. Min Act: -0.1700
Data Index: 7928453 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.7175. Min Act: -0.1700
Data Index: 7232333 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.7487. Min Act: -0.1700
Data Index: 3919345 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.6862. Min Act: -0.1700
Data Index: 6398671 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.6862. Min Act: -0.1700
Data Index: 2751773 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.6550. Min Act: -0.1700
Data Index: 224864 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.6550. Min Act: -0.1700
Data Index: 5142310 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.6237. Min Act: -0.1700
Data Index: 780888 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.6237. Min Act: -0.1700
Data Index: 2470920 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.6237. Min Act: -0.1700
Data Index: 6798042 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.5925. Min Act: -0.1700
Data Index: 197781 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.5925. Min Act: -0.1700
Data Index: 4300163 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.5925. Min Act: -0.1700
Data Index: 3006667 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.5925. Min Act: -0.1700
Data Index: 2758065 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.5612. Min Act: -0.1700
Data Index: 7129829 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1237. Min Range: -6.1237
Max Act: 5.5612. Min Act: -0.1700
Data Index: 4586094 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19