Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3783 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.7261. Min Act: -0.1700
Data Index: 1753232 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.6949. Min Act: -0.1700
Data Index: 6768200 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.7261. Min Act: -0.1700
Data Index: 3814131 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.6949. Min Act: -0.1700
Data Index: 5114991 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.6636. Min Act: -0.1700
Data Index: 8366578 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.6636. Min Act: -0.1700
Data Index: 1753235 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.6636. Min Act: -0.1700
Data Index: 8366571 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.6636. Min Act: -0.1700
Data Index: 7841898 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.6323. Min Act: -0.1700
Data Index: 5307474 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.6323. Min Act: -0.1700
Data Index: 4109111 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.6010. Min Act: -0.1700
Data Index: 5443386 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.6010. Min Act: -0.1700
Data Index: 7824466 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.6010. Min Act: -0.1700
Data Index: 5001890 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.5697. Min Act: -0.1700
Data Index: 1353877 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.5697. Min Act: -0.1700
Data Index: 4608012 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.5697. Min Act: -0.1700
Data Index: 5841244 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.5697. Min Act: -0.1700
Data Index: 6291209 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.5697. Min Act: -0.1700
Data Index: 3240098 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.5697. Min Act: -0.1700
Data Index: 3353480 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7261. Min Range: -3.7261
Max Act: 3.5697. Min Act: -0.1700
Data Index: 3421990 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19