Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1771 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9630. Min Act: -0.1700
Data Index: 455555 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9630. Min Act: -0.1700
Data Index: 6947070 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9630. Min Act: -0.1700
Data Index: 4217430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 3810935 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 6078152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 4998897 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 1335555 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 4084708 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 4002471 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 1248071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 3977117 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 783790 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 3851201 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 751806 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 128862 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 624434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 215825 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 3697868 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 3574199 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9630. Min Range: -4.9630
Max Act: 4.9318. Min Act: -0.1700
Data Index: 544725 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19