Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2861 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.9736. Min Act: -0.1700
Data Index: 4446122 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.9424. Min Act: -0.1700
Data Index: 171075 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.9111. Min Act: -0.1700
Data Index: 8729343 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.8174. Min Act: -0.1700
Data Index: 4694226 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.7236. Min Act: -0.1700
Data Index: 5218677 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.7236. Min Act: -0.1700
Data Index: 7023613 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.6299. Min Act: -0.1700
Data Index: 7023614 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.6611. Min Act: -0.1700
Data Index: 410391 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.6611. Min Act: -0.1700
Data Index: 5596410 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.6299. Min Act: -0.1700
Data Index: 5529467 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5986. Min Act: -0.1700
Data Index: 7023607 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5674. Min Act: -0.1700
Data Index: 7857652 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5674. Min Act: -0.1700
Data Index: 1666750 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5361. Min Act: -0.1700
Data Index: 4042854 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5361. Min Act: -0.1700
Data Index: 7115240 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5361. Min Act: -0.1700
Data Index: 2730775 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5674. Min Act: -0.1700
Data Index: 6733300 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5049. Min Act: -0.1700
Data Index: 6847279 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.4424. Min Act: -0.1700
Data Index: 6247191 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.4736. Min Act: -0.1700
Data Index: 6592525 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19