Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 981 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.3527. Min Act: -0.1700
Data Index: 2927649 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.3527. Min Act: -0.1700
Data Index: 3409422 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.3199. Min Act: -0.1700
Data Index: 4705099 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.3199. Min Act: -0.1700
Data Index: 5153880 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.3035. Min Act: -0.1700
Data Index: 6602660 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.2870. Min Act: -0.1700
Data Index: 5955705 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.2706. Min Act: -0.1700
Data Index: 5933009 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.2870. Min Act: -0.1700
Data Index: 7965940 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.2541. Min Act: -0.1700
Data Index: 7470801 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.2541. Min Act: -0.1700
Data Index: 805324 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.2541. Min Act: -0.1700
Data Index: 7122766 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.2375. Min Act: -0.1700
Data Index: 8820660 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.2375. Min Act: -0.1700
Data Index: 6443641 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.2375. Min Act: -0.1700
Data Index: 3673261 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.2044. Min Act: -0.1699
Data Index: 2466693 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.2210. Min Act: -0.1700
Data Index: 5386414 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.2044. Min Act: -0.1700
Data Index: 748270 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.1878. Min Act: -0.1700
Data Index: 4159554 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.1878. Min Act: -0.1700
Data Index: 4926807 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3527. Min Range: -2.3527
Max Act: 2.1712. Min Act: -0.1700
Data Index: 6671372 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19