Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1715 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.7597. Min Act: -0.1700
Data Index: 4324284 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.6971. Min Act: -0.1700
Data Index: 135596 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.6658. Min Act: -0.1700
Data Index: 2737314 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.6345. Min Act: -0.1700
Data Index: 7698782 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.6345. Min Act: -0.1700
Data Index: 3048984 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.6658. Min Act: -0.1700
Data Index: 6468710 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.6032. Min Act: -0.1700
Data Index: 6984283 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.6032. Min Act: -0.1700
Data Index: 6143588 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.6032. Min Act: -0.1700
Data Index: 1789435 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5719. Min Act: -0.1700
Data Index: 1789430 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5719. Min Act: -0.1700
Data Index: 6984284 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5719. Min Act: -0.1700
Data Index: 895416 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5406. Min Act: -0.1700
Data Index: 5540000 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5406. Min Act: -0.1700
Data Index: 574429 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5406. Min Act: -0.1700
Data Index: 4466939 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.4309. Min Act: -0.1700
Data Index: 1923231 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5406. Min Act: -0.1700
Data Index: 7099846 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5093. Min Act: -0.1700
Data Index: 7460885 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5406. Min Act: -0.1700
Data Index: 6143587 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5093. Min Act: -0.1700
Data Index: 5757907 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19