Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2635 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0235. Min Range: -3.0235
Max Act: 3.0235. Min Act: -0.1700
Data Index: 1805610 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0235. Min Range: -3.0235
Max Act: 3.0077. Min Act: -0.1700
Data Index: 1194151 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0235. Min Range: -3.0235
Max Act: 3.0077. Min Act: -0.1700
Data Index: 333375 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.9128. Min Act: -0.1700
Data Index: 594122 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.8969. Min Act: -0.1700
Data Index: 1661778 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.8969. Min Act: -0.1700
Data Index: 1902167 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.8493. Min Act: -0.1700
Data Index: 2937179 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.8334. Min Act: -0.1700
Data Index: 2461678 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.8334. Min Act: -0.1700
Data Index: 5178265 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.8334. Min Act: -0.1700
Data Index: 6733713 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.8334. Min Act: -0.1700
Data Index: 7357459 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.8175. Min Act: -0.1700
Data Index: 661469 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.8175. Min Act: -0.1700
Data Index: 286910 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.7856. Min Act: -0.1700
Data Index: 6091204 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.7856. Min Act: -0.1700
Data Index: 4743133 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.7697. Min Act: -0.1700
Data Index: 4285789 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.7697. Min Act: -0.1700
Data Index: 6471946 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.7697. Min Act: -0.1700
Data Index: 7540651 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.7537. Min Act: -0.1700
Data Index: 4913403 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0235. Min Range: -3.0235
Max Act: 2.7697. Min Act: -0.1700
Data Index: 2162103 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19