Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3367 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.7932. Min Act: -0.1700
Data Index: 2585528 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.6057. Min Act: -0.1700
Data Index: 3185954 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.4807. Min Act: -0.1700
Data Index: 2751910 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.2932. Min Act: -0.1700
Data Index: 7836558 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.2932. Min Act: -0.1700
Data Index: 3554968 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.2932. Min Act: -0.1700
Data Index: 6798586 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.2932. Min Act: -0.1700
Data Index: 7627346 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.1682. Min Act: -0.1700
Data Index: 1426006 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.1057. Min Act: -0.1700
Data Index: 1965171 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.1057. Min Act: -0.1700
Data Index: 4921556 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.9807. Min Act: -0.1700
Data Index: 5190936 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.0432. Min Act: -0.1700
Data Index: 7303944 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.0432. Min Act: -0.1700
Data Index: 5212288 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.9807. Min Act: -0.1700
Data Index: 4915898 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.9807. Min Act: -0.1700
Data Index: 6532572 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.8557. Min Act: -0.1700
Data Index: 7753921 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.9182. Min Act: -0.1700
Data Index: 8389468 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.9182. Min Act: -0.1700
Data Index: 1939077 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.9182. Min Act: -0.1700
Data Index: 6498702 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.8557. Min Act: -0.1700
Data Index: 6440114 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19