Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6284. Min Range: -9.6284
Max Act: 9.6284. Min Act: -0.1700
Data Index: 3045038 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6284. Min Range: -9.6284
Max Act: 9.5034. Min Act: -0.1700
Data Index: 7150550 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6284. Min Range: -9.6284
Max Act: 9.5034. Min Act: -0.1700
Data Index: 5504145 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6284. Min Range: -9.6284
Max Act: 9.1909. Min Act: -0.1700
Data Index: 4532678 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6284. Min Range: -9.6284
Max Act: 9.0659. Min Act: -0.1700
Data Index: 4969196 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.8784. Min Act: -0.1700
Data Index: 2041537 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.7534. Min Act: -0.1700
Data Index: 8652157 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.6909. Min Act: -0.1700
Data Index: 265404 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.6909. Min Act: -0.1700
Data Index: 484245 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.6909. Min Act: -0.1700
Data Index: 8114255 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.6909. Min Act: -0.1700
Data Index: 4949124 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.6284. Min Act: -0.1700
Data Index: 6514522 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.6284. Min Act: -0.1700
Data Index: 4456083 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.6284. Min Act: -0.1700
Data Index: 3287981 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.5659. Min Act: -0.1700
Data Index: 930076 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.5659. Min Act: -0.1700
Data Index: 118167 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.5659. Min Act: -0.1700
Data Index: 1158300 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.5659. Min Act: -0.1700
Data Index: 6932217 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.5034. Min Act: -0.1700
Data Index: 4825990 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6284. Min Range: -9.6284
Max Act: 8.5034. Min Act: -0.1700
Data Index: 632886 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19