Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5181 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.7314. Min Act: -0.1700
Data Index: 1506251 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.7002. Min Act: -0.1700
Data Index: 7045497 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.5752. Min Act: -0.1700
Data Index: 486216 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.5127. Min Act: -0.1700
Data Index: 1857982 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4814. Min Act: -0.1700
Data Index: 2237289 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4814. Min Act: -0.1700
Data Index: 754740 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4814. Min Act: -0.1700
Data Index: 697654 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4814. Min Act: -0.1700
Data Index: 1332803 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4814. Min Act: -0.1700
Data Index: 6463450 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4502. Min Act: -0.1700
Data Index: 4819322 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4502. Min Act: -0.1700
Data Index: 7433253 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4502. Min Act: -0.1700
Data Index: 369404 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4502. Min Act: -0.1700
Data Index: 4580890 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4189. Min Act: -0.1700
Data Index: 7514231 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4502. Min Act: -0.1700
Data Index: 6681553 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4189. Min Act: -0.1700
Data Index: 1301681 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4189. Min Act: -0.1700
Data Index: 7372486 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4189. Min Act: -0.1700
Data Index: 8180735 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.4502. Min Act: -0.1700
Data Index: 6415681 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.3877. Min Act: -0.1700
Data Index: 6105457 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19