Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.8777. Min Act: -0.1700
Data Index: 5832301 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.7104. Min Act: -0.1700
Data Index: 4865074 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6778. Min Act: -0.1700
Data Index: 1142377 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6778. Min Act: -0.1700
Data Index: 765506 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6778. Min Act: -0.1700
Data Index: 8286883 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6456. Min Act: -0.1700
Data Index: 8023176 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6456. Min Act: -0.1700
Data Index: 6187341 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6296. Min Act: -0.1700
Data Index: 5259378 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6376. Min Act: -0.1700
Data Index: 1392961 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6217. Min Act: -0.1700
Data Index: 5887435 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6138. Min Act: -0.1700
Data Index: 6464330 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6059. Min Act: -0.1700
Data Index: 3038686 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6138. Min Act: -0.1700
Data Index: 2932005 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6138. Min Act: -0.1700
Data Index: 2528034 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6059. Min Act: -0.1700
Data Index: 7133587 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.5980. Min Act: -0.1700
Data Index: 7962267 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.5980. Min Act: -0.1700
Data Index: 3588732 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.5980. Min Act: -0.1700
Data Index: 8322137 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.6059. Min Act: -0.1700
Data Index: 8764701 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8777. Min Range: -0.8777
Max Act: 0.5980. Min Act: -0.1700
Data Index: 4759039 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19