Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2880 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1532. Min Range: -4.1532
Max Act: 4.1532. Min Act: -0.1700
Data Index: 6175439 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.7937. Min Act: -0.1700
Data Index: 3544090 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.7468. Min Act: -0.1700
Data Index: 2089486 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6842. Min Act: -0.1700
Data Index: 4496487 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6686. Min Act: -0.1700
Data Index: 4371366 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6686. Min Act: -0.1700
Data Index: 4285841 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6842. Min Act: -0.1700
Data Index: 3447244 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6842. Min Act: -0.1700
Data Index: 2540627 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6686. Min Act: -0.1700
Data Index: 6866975 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6842. Min Act: -0.1700
Data Index: 2814836 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6529. Min Act: -0.1700
Data Index: 5120138 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6529. Min Act: -0.1700
Data Index: 8415140 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6529. Min Act: -0.1700
Data Index: 1029767 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6373. Min Act: -0.1700
Data Index: 5313457 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6216. Min Act: -0.1700
Data Index: 7214055 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6373. Min Act: -0.1700
Data Index: 3219459 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6216. Min Act: -0.1700
Data Index: 4789973 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6373. Min Act: -0.1700
Data Index: 3081562 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.6216. Min Act: -0.1700
Data Index: 2663884 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1532. Min Range: -4.1532
Max Act: 3.5903. Min Act: -0.1700
Data Index: 494830 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19