Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3780 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.5305. Min Act: -0.1700
Data Index: 6048629 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.4680. Min Act: -0.1700
Data Index: 1199857 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.4680. Min Act: -0.1700
Data Index: 3780061 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.4367. Min Act: -0.1700
Data Index: 5082451 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.4055. Min Act: -0.1700
Data Index: 8297127 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.3742. Min Act: -0.1700
Data Index: 1968477 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.3117. Min Act: -0.1700
Data Index: 784449 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.3117. Min Act: -0.1700
Data Index: 5298958 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.2805. Min Act: -0.1700
Data Index: 5818373 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.2805. Min Act: -0.1700
Data Index: 5344323 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.2180. Min Act: -0.1700
Data Index: 6049964 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.1867. Min Act: -0.1700
Data Index: 5992454 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.1867. Min Act: -0.1700
Data Index: 5850384 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.1867. Min Act: -0.1700
Data Index: 7264281 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.1867. Min Act: -0.1700
Data Index: 1853573 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.1867. Min Act: -0.1700
Data Index: 5491508 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.1555. Min Act: -0.1700
Data Index: 2767672 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.1555. Min Act: -0.1700
Data Index: 4678811 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.1555. Min Act: -0.1700
Data Index: 3541052 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5305. Min Range: -5.5305
Max Act: 5.1555. Min Act: -0.1700
Data Index: 8738351 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19