Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9887. Min Act: -0.1700
Data Index: 2835511 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9887. Min Act: -0.1700
Data Index: 1474971 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9729. Min Act: -0.1700
Data Index: 6136611 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9571. Min Act: -0.1700
Data Index: 7085442 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9571. Min Act: -0.1700
Data Index: 6655539 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9571. Min Act: -0.1700
Data Index: 4104848 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9254. Min Act: -0.1700
Data Index: 4400024 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9571. Min Act: -0.1700
Data Index: 7028314 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9413. Min Act: -0.1700
Data Index: 480802 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9254. Min Act: -0.1700
Data Index: 7047541 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9254. Min Act: -0.1700
Data Index: 2949676 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9096. Min Act: -0.1700
Data Index: 2640610 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9096. Min Act: -0.1700
Data Index: 8538314 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9096. Min Act: -0.1700
Data Index: 3945428 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9096. Min Act: -0.1700
Data Index: 6238578 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9096. Min Act: -0.1700
Data Index: 5682807 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9096. Min Act: -0.1700
Data Index: 6785477 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.8937. Min Act: -0.1700
Data Index: 6603097 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.8937. Min Act: -0.1700
Data Index: 6648681 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.8937. Min Act: -0.1700
Data Index: 4134556 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19