Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2577 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.6307. Min Act: -0.1700
Data Index: 1026008 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.5682. Min Act: -0.1700
Data Index: 1737252 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.5057. Min Act: -0.1700
Data Index: 1002377 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.5057. Min Act: -0.1700
Data Index: 8422095 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.4432. Min Act: -0.1700
Data Index: 2852601 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.4432. Min Act: -0.1700
Data Index: 7650278 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.4120. Min Act: -0.1700
Data Index: 8806983 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.4120. Min Act: -0.1700
Data Index: 2358043 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.3807. Min Act: -0.1700
Data Index: 6983421 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.3807. Min Act: -0.1700
Data Index: 2281391 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.3494. Min Act: -0.1700
Data Index: 5223514 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.3494. Min Act: -0.1700
Data Index: 2747281 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.3494. Min Act: -0.1700
Data Index: 5611715 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.3494. Min Act: -0.1700
Data Index: 5983665 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.3182. Min Act: -0.1700
Data Index: 2233992 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.3182. Min Act: -0.1700
Data Index: 5059625 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.3182. Min Act: -0.1700
Data Index: 2110795 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.3182. Min Act: -0.1700
Data Index: 2415231 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.3182. Min Act: -0.1700
Data Index: 6574337 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6307. Min Range: -4.6307
Max Act: 4.3182. Min Act: -0.1700
Data Index: 1836697 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19