Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.7222. Min Act: -0.1700
Data Index: 3623448 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.6597. Min Act: -0.1700
Data Index: 2500423 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.6597. Min Act: -0.1700
Data Index: 6522381 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.6597. Min Act: -0.1700
Data Index: 2766630 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.5972. Min Act: -0.1700
Data Index: 6926023 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.5347. Min Act: -0.1700
Data Index: 1482063 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.4097. Min Act: -0.1700
Data Index: 1570149 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.4410. Min Act: -0.1700
Data Index: 6153916 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.4097. Min Act: -0.1700
Data Index: 520942 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.3785. Min Act: -0.1700
Data Index: 7293701 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.3472. Min Act: -0.1700
Data Index: 4953188 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.3472. Min Act: -0.1700
Data Index: 1645029 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.3472. Min Act: -0.1700
Data Index: 4937327 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.3160. Min Act: -0.1700
Data Index: 3891268 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.3160. Min Act: -0.1700
Data Index: 6783613 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.3160. Min Act: -0.1700
Data Index: 7680321 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.3160. Min Act: -0.1700
Data Index: 2243233 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.3160. Min Act: -0.1700
Data Index: 1098006 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.2847. Min Act: -0.1700
Data Index: 1716130 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7222. Min Range: -6.7222
Max Act: 6.2847. Min Act: -0.1700
Data Index: 7664094 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19