Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5954 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2435. Min Range: -8.2435
Max Act: 8.2435. Min Act: -0.1700
Data Index: 8053901 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2435. Min Range: -8.2435
Max Act: 8.0872. Min Act: -0.1700
Data Index: 2102508 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2435. Min Range: -8.2435
Max Act: 8.0560. Min Act: -0.1700
Data Index: 535049 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2435. Min Range: -8.2435
Max Act: 8.0247. Min Act: -0.1700
Data Index: 974408 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2435. Min Range: -8.2435
Max Act: 8.0247. Min Act: -0.1700
Data Index: 4479377 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.9935. Min Act: -0.1700
Data Index: 8164392 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.9935. Min Act: -0.1700
Data Index: 46948 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.9622. Min Act: -0.1700
Data Index: 8221683 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.8372. Min Act: -0.1700
Data Index: 3392994 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.8060. Min Act: -0.1700
Data Index: 4884308 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.7747. Min Act: -0.1700
Data Index: 364603 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.7747. Min Act: -0.1700
Data Index: 1570200 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.7435. Min Act: -0.1700
Data Index: 4456250 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.7435. Min Act: -0.1700
Data Index: 2849182 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.7435. Min Act: -0.1700
Data Index: 7491457 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.7122. Min Act: -0.1700
Data Index: 2180030 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.6497. Min Act: -0.1700
Data Index: 3436851 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.6497. Min Act: -0.1700
Data Index: 8766599 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.7122. Min Act: -0.1700
Data Index: 6470220 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2435. Min Range: -8.2435
Max Act: 7.6497. Min Act: -0.1700
Data Index: 4614082 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19