Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4926 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.8696. Min Act: -0.1700
Data Index: 5247645 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.8071. Min Act: -0.1700
Data Index: 1051564 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.7446. Min Act: -0.1700
Data Index: 7406626 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.6821. Min Act: -0.1700
Data Index: 4684258 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.6509. Min Act: -0.1700
Data Index: 1378734 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.6509. Min Act: -0.1700
Data Index: 2405003 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.6509. Min Act: -0.1700
Data Index: 2154340 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.6196. Min Act: -0.1700
Data Index: 6074149 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.5884. Min Act: -0.1700
Data Index: 864198 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.5571. Min Act: -0.1700
Data Index: 5787105 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.5571. Min Act: -0.1700
Data Index: 420414 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.5571. Min Act: -0.1700
Data Index: 669857 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.5884. Min Act: -0.1700
Data Index: 5935076 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.5259. Min Act: -0.1700
Data Index: 272273 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.5259. Min Act: -0.1700
Data Index: 3481265 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.5259. Min Act: -0.1700
Data Index: 570644 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.5259. Min Act: -0.1700
Data Index: 3369676 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.5259. Min Act: -0.1700
Data Index: 2866545 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.5259. Min Act: -0.1700
Data Index: 3062995 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8696. Min Range: -5.8696
Max Act: 5.5259. Min Act: -0.1700
Data Index: 3932950 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19