Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 554 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3350. Min Range: -7.3350
Max Act: 7.3350. Min Act: -0.1700
Data Index: 1087035 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3350. Min Range: -7.3350
Max Act: 7.1163. Min Act: -0.1700
Data Index: 3785226 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3350. Min Range: -7.3350
Max Act: 7.1163. Min Act: -0.1700
Data Index: 8337961 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.9288. Min Act: -0.1700
Data Index: 8161357 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.9288. Min Act: -0.1700
Data Index: 1235774 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.8975. Min Act: -0.1700
Data Index: 4757431 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.8975. Min Act: -0.1700
Data Index: 4983135 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.8663. Min Act: -0.1700
Data Index: 1216703 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.8663. Min Act: -0.1700
Data Index: 2787593 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.8663. Min Act: -0.1700
Data Index: 1205105 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.8663. Min Act: -0.1700
Data Index: 4026515 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.8663. Min Act: -0.1700
Data Index: 4936789 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.8350. Min Act: -0.1700
Data Index: 2317841 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.8038. Min Act: -0.1700
Data Index: 2643129 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.7725. Min Act: -0.1700
Data Index: 941255 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.7725. Min Act: -0.1700
Data Index: 1067551 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.7725. Min Act: -0.1700
Data Index: 316416 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.7725. Min Act: -0.1700
Data Index: 6688463 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.7413. Min Act: -0.1700
Data Index: 4021468 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3350. Min Range: -7.3350
Max Act: 6.7725. Min Act: -0.1700
Data Index: 2850502 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19