Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5735 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.6304. Min Act: -0.1700
Data Index: 4135499 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.5366. Min Act: -0.1700
Data Index: 4385737 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.5366. Min Act: -0.1700
Data Index: 4903996 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.5054. Min Act: -0.1700
Data Index: 3573541 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4741. Min Act: -0.1700
Data Index: 7382291 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4741. Min Act: -0.1700
Data Index: 6911956 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4429. Min Act: -0.1700
Data Index: 3604287 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4116. Min Act: -0.1699
Data Index: 6439166 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4116. Min Act: -0.1700
Data Index: 2798205 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4116. Min Act: -0.1700
Data Index: 6319927 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4116. Min Act: -0.1700
Data Index: 1929720 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3804. Min Act: -0.1700
Data Index: 5790528 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3491. Min Act: -0.1700
Data Index: 5413847 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3491. Min Act: -0.1700
Data Index: 6695588 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3491. Min Act: -0.1700
Data Index: 714796 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3491. Min Act: -0.1700
Data Index: 7451727 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3491. Min Act: -0.1700
Data Index: 5667087 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3804. Min Act: -0.1700
Data Index: 6439159 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3179. Min Act: -0.1700
Data Index: 2872784 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3179. Min Act: -0.1700
Data Index: 5423300 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19