Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.3225. Min Act: -0.1700
Data Index: 6166706 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.2600. Min Act: -0.1700
Data Index: 3575233 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.2600. Min Act: -0.1700
Data Index: 4791306 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.2600. Min Act: -0.1700
Data Index: 1254569 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.2912. Min Act: -0.1700
Data Index: 6079464 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.2287. Min Act: -0.1700
Data Index: 696250 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.1975. Min Act: -0.1700
Data Index: 173850 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.1975. Min Act: -0.1700
Data Index: 7587893 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.1662. Min Act: -0.1700
Data Index: 1807392 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.1662. Min Act: -0.1700
Data Index: 5017928 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.1350. Min Act: -0.1700
Data Index: 2140373 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.1350. Min Act: -0.1700
Data Index: 2925876 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.1350. Min Act: -0.1700
Data Index: 419888 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.1350. Min Act: -0.1700
Data Index: 4295016 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.1350. Min Act: -0.1700
Data Index: 2831642 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.1037. Min Act: -0.1700
Data Index: 164258 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.1037. Min Act: -0.1700
Data Index: 5824842 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.1037. Min Act: -0.1700
Data Index: 7969605 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.1037. Min Act: -0.1700
Data Index: 4926082 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3225. Min Range: -4.3225
Max Act: 4.0725. Min Act: -0.1700
Data Index: 2398217 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19