Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4623 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2689. Min Range: -9.2689
Max Act: 9.2689. Min Act: -0.1700
Data Index: 130226 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2689. Min Range: -9.2689
Max Act: 9.2064. Min Act: -0.1700
Data Index: 833881 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2689. Min Range: -9.2689
Max Act: 9.0189. Min Act: -0.1700
Data Index: 7921068 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2689. Min Range: -9.2689
Max Act: 9.0189. Min Act: -0.1700
Data Index: 7403941 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.9564. Min Act: -0.1700
Data Index: 483686 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.9564. Min Act: -0.1700
Data Index: 4438659 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.8939. Min Act: -0.1700
Data Index: 4438666 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.8939. Min Act: -0.1700
Data Index: 7403940 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.8939. Min Act: -0.1700
Data Index: 1167945 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.8314. Min Act: -0.1700
Data Index: 82678 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.7689. Min Act: -0.1700
Data Index: 6110197 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.7689. Min Act: -0.1700
Data Index: 5811956 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.7689. Min Act: -0.1700
Data Index: 5559213 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.7064. Min Act: -0.1700
Data Index: 7295972 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.7064. Min Act: -0.1700
Data Index: 5607545 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.7064. Min Act: -0.1700
Data Index: 7442716 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.7064. Min Act: -0.1700
Data Index: 6086803 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.5814. Min Act: -0.1700
Data Index: 7194493 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.6439. Min Act: -0.1700
Data Index: 3465919 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2689. Min Range: -9.2689
Max Act: 8.5814. Min Act: -0.1700
Data Index: 2215329 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19