Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2813 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.5697. Min Act: -0.1700
Data Index: 2706750 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.5072. Min Act: -0.1700
Data Index: 469255 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.5072. Min Act: -0.1700
Data Index: 4755902 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4760. Min Act: -0.1700
Data Index: 7811376 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4447. Min Act: -0.1700
Data Index: 5540270 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4447. Min Act: -0.1700
Data Index: 5301172 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4447. Min Act: -0.1700
Data Index: 1153190 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4447. Min Act: -0.1700
Data Index: 2706751 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4447. Min Act: -0.1700
Data Index: 1504076 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4135. Min Act: -0.1700
Data Index: 6070863 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4135. Min Act: -0.1700
Data Index: 4252580 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4135. Min Act: -0.1700
Data Index: 3127992 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4135. Min Act: -0.1700
Data Index: 4474173 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4135. Min Act: -0.1700
Data Index: 3113379 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4135. Min Act: -0.1700
Data Index: 2009257 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.3822. Min Act: -0.1700
Data Index: 5301182 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.3822. Min Act: -0.1700
Data Index: 534748 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.3510. Min Act: -0.1700
Data Index: 5230988 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.3822. Min Act: -0.1700
Data Index: 1146978 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4135. Min Act: -0.1700
Data Index: 5154535 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19