Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 645 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4006. Min Range: -6.4006
Max Act: 6.4006. Min Act: -0.1700
Data Index: 4180166 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4006. Min Range: -6.4006
Max Act: 6.2443. Min Act: -0.1700
Data Index: 4292376 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4006. Min Range: -6.4006
Max Act: 6.2443. Min Act: -0.1700
Data Index: 7228886 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4006. Min Range: -6.4006
Max Act: 6.2131. Min Act: -0.1700
Data Index: 2683803 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4006. Min Range: -6.4006
Max Act: 6.1193. Min Act: -0.1700
Data Index: 2340326 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.9943. Min Act: -0.1700
Data Index: 4142050 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.9631. Min Act: -0.1700
Data Index: 5336084 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.9318. Min Act: -0.1700
Data Index: 5707629 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.9006. Min Act: -0.1700
Data Index: 3835496 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.9006. Min Act: -0.1700
Data Index: 6861105 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.8693. Min Act: -0.1700
Data Index: 7966343 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.9006. Min Act: -0.1700
Data Index: 6328460 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.8381. Min Act: -0.1700
Data Index: 531242 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.8381. Min Act: -0.1700
Data Index: 5930779 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.8693. Min Act: -0.1700
Data Index: 1143440 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.8381. Min Act: -0.1700
Data Index: 6245745 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.8068. Min Act: -0.1700
Data Index: 7019376 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.8068. Min Act: -0.1700
Data Index: 7708322 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.7756. Min Act: -0.1700
Data Index: 7538422 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4006. Min Range: -6.4006
Max Act: 5.7756. Min Act: -0.1700
Data Index: 6284113 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19