Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 716 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2268. Min Range: -5.2268
Max Act: 5.2268. Min Act: -0.1700
Data Index: 3516228 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2268. Min Range: -5.2268
Max Act: 5.2268. Min Act: -0.1700
Data Index: 7785281 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2268. Min Range: -5.2268
Max Act: 5.1643. Min Act: -0.1700
Data Index: 6618212 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2268. Min Range: -5.2268
Max Act: 5.1956. Min Act: -0.1700
Data Index: 1257918 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2268. Min Range: -5.2268
Max Act: 5.0706. Min Act: -0.1700
Data Index: 5842228 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2268. Min Range: -5.2268
Max Act: 5.0706. Min Act: -0.1700
Data Index: 3413687 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2268. Min Range: -5.2268
Max Act: 5.0081. Min Act: -0.1700
Data Index: 1598660 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2268. Min Range: -5.2268
Max Act: 5.0081. Min Act: -0.1700
Data Index: 8628432 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2268. Min Range: -5.2268
Max Act: 5.0081. Min Act: -0.1700
Data Index: 6094858 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2268. Min Range: -5.2268
Max Act: 4.9456. Min Act: -0.1700
Data Index: 5123832 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2268. Min Range: -5.2268
Max Act: 4.9456. Min Act: -0.1700
Data Index: 5525442 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2268. Min Range: -5.2268
Max Act: 4.9456. Min Act: -0.1700
Data Index: 5260331 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2268. Min Range: -5.2268
Max Act: 4.9456. Min Act: -0.1700
Data Index: 7798530 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2268. Min Range: -5.2268
Max Act: 4.9143. Min Act: -0.1700
Data Index: 3499665 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2268. Min Range: -5.2268
Max Act: 4.9456. Min Act: -0.1700
Data Index: 4652207 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2268. Min Range: -5.2268
Max Act: 4.9143. Min Act: -0.1700
Data Index: 7393635 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2268. Min Range: -5.2268
Max Act: 4.9143. Min Act: -0.1700
Data Index: 3962138 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2268. Min Range: -5.2268
Max Act: 4.8831. Min Act: -0.1700
Data Index: 7323036 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2268. Min Range: -5.2268
Max Act: 4.9143. Min Act: -0.1700
Data Index: 2715556 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2268. Min Range: -5.2268
Max Act: 4.9143. Min Act: -0.1700
Data Index: 6226281 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19