Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1587 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.8051. Min Act: -0.1700
Data Index: 4669364 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.8051. Min Act: -0.1700
Data Index: 4741617 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.7739. Min Act: -0.1700
Data Index: 6883571 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.7113. Min Act: -0.1700
Data Index: 3151011 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.7113. Min Act: -0.1700
Data Index: 3293913 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.7113. Min Act: -0.1700
Data Index: 301140 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.7113. Min Act: -0.1700
Data Index: 7115905 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.7113. Min Act: -0.1700
Data Index: 1496573 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.6957. Min Act: -0.1700
Data Index: 1254647 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.6957. Min Act: -0.1700
Data Index: 3063845 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.6957. Min Act: -0.1700
Data Index: 2002214 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.6644. Min Act: -0.1700
Data Index: 822431 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.6957. Min Act: -0.1700
Data Index: 5758508 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.6487. Min Act: -0.1700
Data Index: 1660630 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.6487. Min Act: -0.1700
Data Index: 5083069 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.6487. Min Act: -0.1700
Data Index: 2416400 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.6331. Min Act: -0.1700
Data Index: 5020948 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.6644. Min Act: -0.1700
Data Index: 3687589 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.6331. Min Act: -0.1700
Data Index: 2373877 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8051. Min Range: -3.8051
Max Act: 3.6644. Min Act: -0.1700
Data Index: 4007576 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19