Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 815 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1843. Min Range: -3.1843
Max Act: 3.1843. Min Act: -0.1700
Data Index: 3046282 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1843. Min Range: -3.1843
Max Act: 3.0109. Min Act: -0.1700
Data Index: 2651006 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.9477. Min Act: -0.1700
Data Index: 7803215 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.9160. Min Act: -0.1700
Data Index: 918219 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.9002. Min Act: -0.1700
Data Index: 2677031 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.9002. Min Act: -0.1700
Data Index: 4960234 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.9319. Min Act: -0.1700
Data Index: 6635466 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.9002. Min Act: -0.1700
Data Index: 2133734 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.8525. Min Act: -0.1700
Data Index: 381728 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.8684. Min Act: -0.1700
Data Index: 476214 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.8366. Min Act: -0.1700
Data Index: 1197958 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.8048. Min Act: -0.1700
Data Index: 2468247 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.8048. Min Act: -0.1700
Data Index: 5403913 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.8207. Min Act: -0.1700
Data Index: 417916 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.8366. Min Act: -0.1700
Data Index: 4289316 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.8207. Min Act: -0.1700
Data Index: 2201555 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.8207. Min Act: -0.1700
Data Index: 8402210 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.7889. Min Act: -0.1700
Data Index: 4028213 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.7570. Min Act: -0.1700
Data Index: 3806063 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1843. Min Range: -3.1843
Max Act: 2.7570. Min Act: -0.1700
Data Index: 4007249 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19