Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0410. Min Range: -7.0410
Max Act: 7.0410. Min Act: -0.1700
Data Index: 3314623 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0410. Min Range: -7.0410
Max Act: 7.0410. Min Act: -0.1700
Data Index: 7304517 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0410. Min Range: -7.0410
Max Act: 7.0410. Min Act: -0.1700
Data Index: 5423823 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.9785. Min Act: -0.1700
Data Index: 6455568 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.9472. Min Act: -0.1700
Data Index: 4828645 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.8535. Min Act: -0.1700
Data Index: 548384 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.8222. Min Act: -0.1700
Data Index: 1162883 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.8222. Min Act: -0.1700
Data Index: 4297811 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.8222. Min Act: -0.1700
Data Index: 7207373 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.8222. Min Act: -0.1700
Data Index: 3771447 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.7910. Min Act: -0.1700
Data Index: 2678770 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.7597. Min Act: -0.1700
Data Index: 7526237 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.7285. Min Act: -0.1700
Data Index: 672216 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.7285. Min Act: -0.1700
Data Index: 3168937 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.6972. Min Act: -0.1700
Data Index: 2739731 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.6972. Min Act: -0.1700
Data Index: 684140 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.6660. Min Act: -0.1700
Data Index: 2960035 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.6347. Min Act: -0.1700
Data Index: 1685420 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.6347. Min Act: -0.1700
Data Index: 407357 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.6035. Min Act: -0.1700
Data Index: 7101545 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19