Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 991 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3643. Min Act: -0.1700
Data Index: 5767236 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3643. Min Act: -0.1700
Data Index: 4384470 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3330. Min Act: -0.1700
Data Index: 986930 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3330. Min Act: -0.1700
Data Index: 1548010 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3330. Min Act: -0.1700
Data Index: 4225510 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3330. Min Act: -0.1700
Data Index: 5952750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3330. Min Act: -0.1700
Data Index: 2023043 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3330. Min Act: -0.1700
Data Index: 7970049 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3330. Min Act: -0.1700
Data Index: 6319389 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3016. Min Act: -0.1700
Data Index: 237877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3016. Min Act: -0.1700
Data Index: 2654189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3016. Min Act: -0.1700
Data Index: 3308340 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3330. Min Act: -0.1700
Data Index: 113299 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3016. Min Act: -0.1700
Data Index: 7293894 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3016. Min Act: -0.1700
Data Index: 3618142 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3016. Min Act: -0.1700
Data Index: 2374389 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3016. Min Act: -0.1700
Data Index: 5178116 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3016. Min Act: -0.1700
Data Index: 5245578 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3016. Min Act: -0.1700
Data Index: 7590172 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3643. Min Range: -3.3643
Max Act: 3.3016. Min Act: -0.1700
Data Index: 759197 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19