Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 187 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.4347. Min Act: -0.1700
Data Index: 1009569 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.4347. Min Act: -0.1700
Data Index: 6366235 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.4347. Min Act: -0.1700
Data Index: 6880983 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.4184. Min Act: -0.1700
Data Index: 3915186 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3858. Min Act: -0.1700
Data Index: 1511222 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3695. Min Act: -0.1700
Data Index: 2484663 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3695. Min Act: -0.1700
Data Index: 144323 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3695. Min Act: -0.1700
Data Index: 4497298 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3531. Min Act: -0.1700
Data Index: 6296708 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3531. Min Act: -0.1700
Data Index: 7467475 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3531. Min Act: -0.1700
Data Index: 3831008 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3695. Min Act: -0.1700
Data Index: 3026841 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3531. Min Act: -0.1700
Data Index: 8322310 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3531. Min Act: -0.1700
Data Index: 1157219 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3531. Min Act: -0.1700
Data Index: 1040808 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3531. Min Act: -0.1700
Data Index: 7790055 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3531. Min Act: -0.1700
Data Index: 5674614 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3367. Min Act: -0.1700
Data Index: 2005659 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3367. Min Act: -0.1700
Data Index: 796623 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4347. Min Range: -2.4347
Max Act: 2.3039. Min Act: -0.1700
Data Index: 6616054 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19