Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2977 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.5559. Min Act: -0.1700
Data Index: 6712325 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.4622. Min Act: -0.1700
Data Index: 6317676 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.4622. Min Act: -0.1700
Data Index: 7403565 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.4309. Min Act: -0.1700
Data Index: 2845501 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.4309. Min Act: -0.1700
Data Index: 5452450 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.4309. Min Act: -0.1700
Data Index: 7052845 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.3997. Min Act: -0.1700
Data Index: 7119595 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.3684. Min Act: -0.1700
Data Index: 5504776 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.3684. Min Act: -0.1700
Data Index: 6959034 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.3372. Min Act: -0.1700
Data Index: 3448101 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.3059. Min Act: -0.1700
Data Index: 6935438 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.3059. Min Act: -0.1700
Data Index: 1119923 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.3059. Min Act: -0.1700
Data Index: 7209127 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.2747. Min Act: -0.1700
Data Index: 3117023 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.2434. Min Act: -0.1700
Data Index: 2030226 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.2434. Min Act: -0.1700
Data Index: 221391 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.2434. Min Act: -0.1700
Data Index: 595371 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.2434. Min Act: -0.1700
Data Index: 790947 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.2434. Min Act: -0.1700
Data Index: 7744512 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5559. Min Range: -5.5559
Max Act: 5.2434. Min Act: -0.1700
Data Index: 1462971 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19