Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 843 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.7791. Min Act: -0.1700
Data Index: 4799170 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.7631. Min Act: -0.1700
Data Index: 959068 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.7312. Min Act: -0.1700
Data Index: 5218168 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.7312. Min Act: -0.1700
Data Index: 6304688 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.7312. Min Act: -0.1700
Data Index: 5704194 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.7312. Min Act: -0.1700
Data Index: 7859883 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6992. Min Act: -0.1700
Data Index: 8245248 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6832. Min Act: -0.1700
Data Index: 6407481 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6672. Min Act: -0.1700
Data Index: 1030248 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6672. Min Act: -0.1700
Data Index: 1337349 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6672. Min Act: -0.1700
Data Index: 8006077 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6512. Min Act: -0.1700
Data Index: 8557869 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6512. Min Act: -0.1700
Data Index: 1634266 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6672. Min Act: -0.1700
Data Index: 1493047 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6351. Min Act: -0.1700
Data Index: 171344 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6512. Min Act: -0.1700
Data Index: 3722108 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6351. Min Act: -0.1700
Data Index: 7537235 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6190. Min Act: -0.1700
Data Index: 5022243 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6190. Min Act: -0.1700
Data Index: 5079021 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7791. Min Range: -2.7791
Max Act: 2.6351. Min Act: -0.1700
Data Index: 5127723 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19