Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.9950. Min Act: -0.1700
Data Index: 6894446 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.8075. Min Act: -0.1700
Data Index: 4488303 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.8075. Min Act: -0.1700
Data Index: 118535 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.7450. Min Act: -0.1700
Data Index: 3835602 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.7450. Min Act: -0.1700
Data Index: 198648 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.7450. Min Act: -0.1700
Data Index: 3014702 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.7138. Min Act: -0.1700
Data Index: 3287341 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.7138. Min Act: -0.1700
Data Index: 4605495 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.7138. Min Act: -0.1700
Data Index: 2209573 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.7138. Min Act: -0.1700
Data Index: 6697571 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.6825. Min Act: -0.1700
Data Index: 183572 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.6825. Min Act: -0.1700
Data Index: 1160286 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.6513. Min Act: -0.1700
Data Index: 2857165 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.6513. Min Act: -0.1700
Data Index: 4787347 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.6825. Min Act: -0.1700
Data Index: 1560114 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.6513. Min Act: -0.1700
Data Index: 3896679 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.6200. Min Act: -0.1700
Data Index: 1299880 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.6200. Min Act: -0.1700
Data Index: 7660990 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.6200. Min Act: -0.1700
Data Index: 4163869 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9950. Min Range: -6.9950
Max Act: 6.5888. Min Act: -0.1700
Data Index: 1983356 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19