Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2945 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1335. Min Range: -7.1335
Max Act: 7.1335. Min Act: -0.1700
Data Index: 1938007 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.8522. Min Act: -0.1700
Data Index: 1118953 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.7585. Min Act: -0.1700
Data Index: 7877742 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.7585. Min Act: -0.1700
Data Index: 2036075 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.7585. Min Act: -0.1700
Data Index: 7718035 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.7585. Min Act: -0.1700
Data Index: 896888 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.7272. Min Act: -0.1700
Data Index: 5699088 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.7272. Min Act: -0.1700
Data Index: 6539562 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.6647. Min Act: -0.1700
Data Index: 8112801 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.6335. Min Act: -0.1700
Data Index: 5252703 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.6022. Min Act: -0.1700
Data Index: 4592312 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.5397. Min Act: -0.1700
Data Index: 1048708 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.5710. Min Act: -0.1700
Data Index: 5235088 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.5397. Min Act: -0.1700
Data Index: 7304490 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.5710. Min Act: -0.1700
Data Index: 3512714 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.5397. Min Act: -0.1700
Data Index: 1858639 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.5397. Min Act: -0.1700
Data Index: 7644697 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.5397. Min Act: -0.1700
Data Index: 4185828 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.5085. Min Act: -0.1700
Data Index: 6505171 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1335. Min Range: -7.1335
Max Act: 6.5085. Min Act: -0.1700
Data Index: 1770740 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19