Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.7410. Min Act: -0.1700
Data Index: 8568951 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.6160. Min Act: -0.1700
Data Index: 5591987 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.6160. Min Act: -0.1700
Data Index: 7002164 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.5848. Min Act: -0.1700
Data Index: 5974503 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.4285. Min Act: -0.1700
Data Index: 1913979 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.4285. Min Act: -0.1700
Data Index: 1704799 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.4285. Min Act: -0.1700
Data Index: 5459130 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.4598. Min Act: -0.1700
Data Index: 7506113 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.4285. Min Act: -0.1700
Data Index: 2162987 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.4285. Min Act: -0.1700
Data Index: 5046505 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.3973. Min Act: -0.1700
Data Index: 630089 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.3973. Min Act: -0.1700
Data Index: 5812994 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.3973. Min Act: -0.1700
Data Index: 2685993 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.3973. Min Act: -0.1700
Data Index: 135221 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.3660. Min Act: -0.1700
Data Index: 6244584 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.4285. Min Act: -0.1700
Data Index: 7127887 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.3973. Min Act: -0.1700
Data Index: 6759955 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.3973. Min Act: -0.1700
Data Index: 2888814 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.4285. Min Act: -0.1700
Data Index: 3300875 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7410. Min Range: -5.7410
Max Act: 5.3973. Min Act: -0.1700
Data Index: 2202673 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19