Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3817 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4044. Min Range: -5.4044
Max Act: 5.4044. Min Act: -0.1700
Data Index: 8651625 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4044. Min Range: -5.4044
Max Act: 5.2482. Min Act: -0.1700
Data Index: 7793760 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4044. Min Range: -5.4044
Max Act: 5.1544. Min Act: -0.1700
Data Index: 2688580 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4044. Min Range: -5.4044
Max Act: 5.1232. Min Act: -0.1700
Data Index: 1485302 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4044. Min Range: -5.4044
Max Act: 5.0919. Min Act: -0.1700
Data Index: 8188846 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4044. Min Range: -5.4044
Max Act: 5.0607. Min Act: -0.1700
Data Index: 5472279 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4044. Min Range: -5.4044
Max Act: 5.0294. Min Act: -0.1700
Data Index: 4567330 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4044. Min Range: -5.4044
Max Act: 5.0294. Min Act: -0.1700
Data Index: 3218457 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4044. Min Range: -5.4044
Max Act: 5.0294. Min Act: -0.1700
Data Index: 3226232 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4044. Min Range: -5.4044
Max Act: 5.0294. Min Act: -0.1700
Data Index: 5581763 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4044. Min Range: -5.4044
Max Act: 4.9982. Min Act: -0.1700
Data Index: 4856441 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4044. Min Range: -5.4044
Max Act: 4.9982. Min Act: -0.1700
Data Index: 4226280 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4044. Min Range: -5.4044
Max Act: 4.9982. Min Act: -0.1700
Data Index: 4446868 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4044. Min Range: -5.4044
Max Act: 4.9669. Min Act: -0.1700
Data Index: 7713888 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4044. Min Range: -5.4044
Max Act: 4.9669. Min Act: -0.1700
Data Index: 8829048 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4044. Min Range: -5.4044
Max Act: 4.9669. Min Act: -0.1700
Data Index: 471388 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4044. Min Range: -5.4044
Max Act: 4.9669. Min Act: -0.1700
Data Index: 8697137 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4044. Min Range: -5.4044
Max Act: 4.9044. Min Act: -0.1700
Data Index: 6157200 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4044. Min Range: -5.4044
Max Act: 4.9357. Min Act: -0.1700
Data Index: 4221927 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4044. Min Range: -5.4044
Max Act: 4.9357. Min Act: -0.1700
Data Index: 7771918 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19