Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.8164. Min Act: -0.1700
Data Index: 2414764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.7852. Min Act: -0.1700
Data Index: 2648218 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.7226. Min Act: -0.1699
Data Index: 5595313 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.7539. Min Act: -0.1700
Data Index: 739335 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.7539. Min Act: -0.1700
Data Index: 7869511 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.7539. Min Act: -0.1700
Data Index: 7998974 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.7539. Min Act: -0.1700
Data Index: 8793571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.7539. Min Act: -0.1700
Data Index: 313959 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.7539. Min Act: -0.1700
Data Index: 5267052 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.7226. Min Act: -0.1700
Data Index: 6174299 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.7226. Min Act: -0.1700
Data Index: 1095516 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.7226. Min Act: -0.1700
Data Index: 5413982 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.7226. Min Act: -0.1700
Data Index: 18155 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.6913. Min Act: -0.1700
Data Index: 8820186 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.6600. Min Act: -0.1700
Data Index: 8772547 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.6913. Min Act: -0.1700
Data Index: 7065573 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.6600. Min Act: -0.1700
Data Index: 2118972 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.6600. Min Act: -0.1700
Data Index: 938656 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.6287. Min Act: -0.1700
Data Index: 2216901 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8164. Min Range: -3.8164
Max Act: 3.6600. Min Act: -0.1700
Data Index: 524814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19