Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1568 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.8693. Min Act: -0.1700
Data Index: 5503774 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.7755. Min Act: -0.1700
Data Index: 1561049 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.6818. Min Act: -0.1700
Data Index: 6412379 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.6818. Min Act: -0.1700
Data Index: 6922942 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.5880. Min Act: -0.1700
Data Index: 7949733 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.4318. Min Act: -0.1700
Data Index: 8023148 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.3693. Min Act: -0.1700
Data Index: 3347827 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.2755. Min Act: -0.1700
Data Index: 7199094 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.2755. Min Act: -0.1700
Data Index: 6118572 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.3068. Min Act: -0.1700
Data Index: 4293342 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.2130. Min Act: -0.1700
Data Index: 7107342 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.1818. Min Act: -0.1700
Data Index: 8377736 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.1818. Min Act: -0.1700
Data Index: 2062803 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.1193. Min Act: -0.1700
Data Index: 3359702 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.1505. Min Act: -0.1700
Data Index: 6707545 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.0880. Min Act: -0.1700
Data Index: 2162125 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.0568. Min Act: -0.1700
Data Index: 4502020 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.0568. Min Act: -0.1700
Data Index: 7714631 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.0880. Min Act: -0.1700
Data Index: 577101 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8693. Min Range: -5.8693
Max Act: 5.0880. Min Act: -0.1700
Data Index: 5683101 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19