Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0587. Min Range: -3.0587
Max Act: 3.0587. Min Act: -0.1700
Data Index: 1568744 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0587. Min Range: -3.0587
Max Act: 3.0587. Min Act: -0.1700
Data Index: 7849446 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0587. Min Range: -3.0587
Max Act: 3.0271. Min Act: -0.1700
Data Index: 5696236 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0587. Min Range: -3.0587
Max Act: 3.0113. Min Act: -0.1700
Data Index: 3803539 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.9639. Min Act: -0.1700
Data Index: 97689 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.9639. Min Act: -0.1700
Data Index: 6737795 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.9322. Min Act: -0.1700
Data Index: 7931973 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.9322. Min Act: -0.1700
Data Index: 2641670 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.9322. Min Act: -0.1700
Data Index: 2484699 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.9005. Min Act: -0.1700
Data Index: 2026745 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8847. Min Act: -0.1700
Data Index: 759962 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8847. Min Act: -0.1700
Data Index: 1034471 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8847. Min Act: -0.1700
Data Index: 1481738 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8688. Min Act: -0.1700
Data Index: 1074432 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8847. Min Act: -0.1700
Data Index: 1504162 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8847. Min Act: -0.1700
Data Index: 4637054 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8847. Min Act: -0.1700
Data Index: 484796 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8688. Min Act: -0.1700
Data Index: 2419210 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8688. Min Act: -0.1700
Data Index: 4610980 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0587. Min Range: -3.0587
Max Act: 2.8688. Min Act: -0.1700
Data Index: 2563014 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19