Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2834 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2160. Min Range: -5.2160
Max Act: 5.2160. Min Act: -0.1700
Data Index: 8060758 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2160. Min Range: -5.2160
Max Act: 5.0910. Min Act: -0.1700
Data Index: 8139931 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2160. Min Range: -5.2160
Max Act: 5.0597. Min Act: -0.1700
Data Index: 1535895 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2160. Min Range: -5.2160
Max Act: 5.0285. Min Act: -0.1700
Data Index: 4325983 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.9972. Min Act: -0.1700
Data Index: 4679134 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.9347. Min Act: -0.1700
Data Index: 945315 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.9347. Min Act: -0.1700
Data Index: 4601415 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.9035. Min Act: -0.1700
Data Index: 5598796 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.8722. Min Act: -0.1700
Data Index: 4772139 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.9035. Min Act: -0.1700
Data Index: 7055133 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.8410. Min Act: -0.1700
Data Index: 7361629 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.8410. Min Act: -0.1700
Data Index: 1842890 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.8097. Min Act: -0.1700
Data Index: 236570 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.8097. Min Act: -0.1700
Data Index: 6579209 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.8097. Min Act: -0.1700
Data Index: 6078261 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.8097. Min Act: -0.1700
Data Index: 5912506 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.7785. Min Act: -0.1700
Data Index: 2692653 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.7785. Min Act: -0.1700
Data Index: 4679297 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.7472. Min Act: -0.1700
Data Index: 225015 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2160. Min Range: -5.2160
Max Act: 4.7785. Min Act: -0.1700
Data Index: 3688797 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19