Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.7932. Min Act: -0.1700
Data Index: 570627 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.6682. Min Act: -0.1700
Data Index: 4594821 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.6369. Min Act: -0.1700
Data Index: 3930813 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.6057. Min Act: -0.1700
Data Index: 3771939 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.5432. Min Act: -0.1700
Data Index: 1420580 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.5744. Min Act: -0.1700
Data Index: 955132 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.5432. Min Act: -0.1700
Data Index: 2619674 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.5432. Min Act: -0.1700
Data Index: 2931631 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.5119. Min Act: -0.1700
Data Index: 306025 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.5119. Min Act: -0.1700
Data Index: 144277 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.4807. Min Act: -0.1700
Data Index: 6607073 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.4807. Min Act: -0.1700
Data Index: 7461164 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.4807. Min Act: -0.1700
Data Index: 7525581 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.4807. Min Act: -0.1700
Data Index: 6146860 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.4807. Min Act: -0.1700
Data Index: 2319801 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.4494. Min Act: -0.1700
Data Index: 2131551 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.4182. Min Act: -0.1700
Data Index: 4097276 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.4494. Min Act: -0.1700
Data Index: 7219587 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.4494. Min Act: -0.1700
Data Index: 851527 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7932. Min Range: -5.7932
Max Act: 5.4494. Min Act: -0.1700
Data Index: 642937 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19