Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3173 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.8089. Min Act: -0.1700
Data Index: 3693825 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.7611. Min Act: -0.1700
Data Index: 6983021 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6812. Min Act: -0.1700
Data Index: 3389972 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.7132. Min Act: -0.1700
Data Index: 1698438 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6651. Min Act: -0.1700
Data Index: 2335283 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6491. Min Act: -0.1700
Data Index: 1810957 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6491. Min Act: -0.1700
Data Index: 5377053 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6330. Min Act: -0.1700
Data Index: 6550689 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6330. Min Act: -0.1700
Data Index: 8235057 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6170. Min Act: -0.1700
Data Index: 5654331 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6330. Min Act: -0.1700
Data Index: 6716751 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6170. Min Act: -0.1700
Data Index: 333568 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6330. Min Act: -0.1700
Data Index: 8113137 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6170. Min Act: -0.1700
Data Index: 4933423 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6330. Min Act: -0.1700
Data Index: 7778425 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6009. Min Act: -0.1700
Data Index: 4200362 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6009. Min Act: -0.1700
Data Index: 5619759 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6170. Min Act: -0.1700
Data Index: 3121987 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6009. Min Act: -0.1700
Data Index: 2662532 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8089. Min Range: -2.8089
Max Act: 2.6170. Min Act: -0.1700
Data Index: 4200366 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19