Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4156 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1316. Min Range: -3.1316
Max Act: 3.1316. Min Act: -0.1700
Data Index: 3992777 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1316. Min Range: -3.1316
Max Act: 3.1316. Min Act: -0.1700
Data Index: 3695848 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1316. Min Range: -3.1316
Max Act: 3.0843. Min Act: -0.1700
Data Index: 879616 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1316. Min Range: -3.1316
Max Act: 3.0843. Min Act: -0.1700
Data Index: 6653855 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1316. Min Range: -3.1316
Max Act: 3.1000. Min Act: -0.1700
Data Index: 879620 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1316. Min Range: -3.1316
Max Act: 3.0527. Min Act: -0.1700
Data Index: 8052413 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1316. Min Range: -3.1316
Max Act: 3.0685. Min Act: -0.1700
Data Index: 3226769 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1316. Min Range: -3.1316
Max Act: 3.0370. Min Act: -0.1700
Data Index: 7755243 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1316. Min Range: -3.1316
Max Act: 3.0212. Min Act: -0.1700
Data Index: 684370 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1316. Min Range: -3.1316
Max Act: 3.0212. Min Act: -0.1700
Data Index: 5340302 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1316. Min Range: -3.1316
Max Act: 3.0054. Min Act: -0.1700
Data Index: 5875334 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1316. Min Range: -3.1316
Max Act: 3.0054. Min Act: -0.1700
Data Index: 7274546 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1316. Min Range: -3.1316
Max Act: 3.0054. Min Act: -0.1700
Data Index: 1959850 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1316. Min Range: -3.1316
Max Act: 2.9896. Min Act: -0.1700
Data Index: 943452 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1316. Min Range: -3.1316
Max Act: 2.9896. Min Act: -0.1700
Data Index: 5016617 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1316. Min Range: -3.1316
Max Act: 2.9896. Min Act: -0.1700
Data Index: 5732570 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1316. Min Range: -3.1316
Max Act: 2.9896. Min Act: -0.1700
Data Index: 2693159 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1316. Min Range: -3.1316
Max Act: 2.9737. Min Act: -0.1700
Data Index: 4759077 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1316. Min Range: -3.1316
Max Act: 2.9737. Min Act: -0.1700
Data Index: 2379260 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1316. Min Range: -3.1316
Max Act: 2.9579. Min Act: -0.1700
Data Index: 463333 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19