Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 384 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.5440. Min Act: -0.1700
Data Index: 6535647 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.4815. Min Act: -0.1700
Data Index: 412150 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.4190. Min Act: -0.1700
Data Index: 7089878 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.3565. Min Act: -0.1700
Data Index: 7735465 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.3253. Min Act: -0.1700
Data Index: 7377114 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.3253. Min Act: -0.1700
Data Index: 7202847 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.2628. Min Act: -0.1700
Data Index: 7476321 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.2628. Min Act: -0.1700
Data Index: 6539021 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.2628. Min Act: -0.1700
Data Index: 738811 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.2940. Min Act: -0.1700
Data Index: 991498 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.2628. Min Act: -0.1700
Data Index: 4270883 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.2315. Min Act: -0.1700
Data Index: 6118708 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.2628. Min Act: -0.1700
Data Index: 2628553 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.2628. Min Act: -0.1700
Data Index: 4154122 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.2628. Min Act: -0.1700
Data Index: 2149574 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.2003. Min Act: -0.1700
Data Index: 6953716 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.2315. Min Act: -0.1700
Data Index: 2755194 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.2003. Min Act: -0.1700
Data Index: 7158681 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.1690. Min Act: -0.1700
Data Index: 2184080 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5440. Min Range: -4.5440
Max Act: 4.2315. Min Act: -0.1700
Data Index: 7561393 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19