Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4398 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.3822. Min Act: -0.1700
Data Index: 5249706 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.2572. Min Act: -0.1700
Data Index: 3060568 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.2885. Min Act: -0.1700
Data Index: 6039342 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.2572. Min Act: -0.1700
Data Index: 3639015 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.1635. Min Act: -0.1700
Data Index: 365748 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.1635. Min Act: -0.1700
Data Index: 8785594 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.1010. Min Act: -0.1700
Data Index: 4823560 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.1635. Min Act: -0.1700
Data Index: 3834221 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.0697. Min Act: -0.1700
Data Index: 2048449 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.0697. Min Act: -0.1700
Data Index: 5043802 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.0072. Min Act: -0.1700
Data Index: 7298067 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.0072. Min Act: -0.1700
Data Index: 4114881 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.0072. Min Act: -0.1700
Data Index: 7985399 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.0072. Min Act: -0.1700
Data Index: 4790362 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3822. Min Range: -5.3822
Max Act: 5.0072. Min Act: -0.1700
Data Index: 1474983 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3822. Min Range: -5.3822
Max Act: 4.9760. Min Act: -0.1700
Data Index: 5394143 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3822. Min Range: -5.3822
Max Act: 4.9760. Min Act: -0.1700
Data Index: 1808824 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3822. Min Range: -5.3822
Max Act: 4.9447. Min Act: -0.1700
Data Index: 3289439 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3822. Min Range: -5.3822
Max Act: 4.9447. Min Act: -0.1700
Data Index: 1169 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3822. Min Range: -5.3822
Max Act: 4.9447. Min Act: -0.1700
Data Index: 938422 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19