Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2558 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.9953. Min Act: -0.1700
Data Index: 1007316 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.8703. Min Act: -0.1700
Data Index: 1517366 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.8078. Min Act: -0.1700
Data Index: 5671198 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.7141. Min Act: -0.1700
Data Index: 2245299 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.7141. Min Act: -0.1700
Data Index: 2459463 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.6828. Min Act: -0.1700
Data Index: 846120 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.6203. Min Act: -0.1700
Data Index: 7030089 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.6516. Min Act: -0.1700
Data Index: 5940321 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.5578. Min Act: -0.1700
Data Index: 6417452 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.5891. Min Act: -0.1700
Data Index: 596742 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.5891. Min Act: -0.1700
Data Index: 5292301 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.5578. Min Act: -0.1700
Data Index: 5309158 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.5266. Min Act: -0.1700
Data Index: 3454486 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.5266. Min Act: -0.1700
Data Index: 375346 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.4953. Min Act: -0.1700
Data Index: 4252467 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.4641. Min Act: -0.1700
Data Index: 685965 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.5266. Min Act: -0.1700
Data Index: 5855987 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.4953. Min Act: -0.1700
Data Index: 3585417 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.4641. Min Act: -0.1700
Data Index: 4395816 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9953. Min Range: -5.9953
Max Act: 5.4641. Min Act: -0.1700
Data Index: 2439235 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19