Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5880 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.3183. Min Act: -0.1700
Data Index: 7506445 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.2558. Min Act: -0.1700
Data Index: 601854 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.2246. Min Act: -0.1700
Data Index: 1368782 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.1933. Min Act: -0.1700
Data Index: 7888444 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.1308. Min Act: -0.1700
Data Index: 4732378 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.1308. Min Act: -0.1700
Data Index: 8236463 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.1308. Min Act: -0.1700
Data Index: 6927368 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.0996. Min Act: -0.1700
Data Index: 1540031 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.0996. Min Act: -0.1700
Data Index: 3181265 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.0996. Min Act: -0.1700
Data Index: 3896405 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.1308. Min Act: -0.1700
Data Index: 614330 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.0996. Min Act: -0.1700
Data Index: 1125750 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.0683. Min Act: -0.1700
Data Index: 2500409 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.0996. Min Act: -0.1700
Data Index: 1858767 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.0996. Min Act: -0.1700
Data Index: 5882235 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.0371. Min Act: -0.1700
Data Index: 1727853 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.0996. Min Act: -0.1700
Data Index: 432429 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.0683. Min Act: -0.1700
Data Index: 819265 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.0996. Min Act: -0.1700
Data Index: 3747571 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3183. Min Range: -6.3183
Max Act: 6.0683. Min Act: -0.1700
Data Index: 7028791 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19