Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 967 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1548. Min Range: -9.1548
Max Act: 9.1548. Min Act: -0.1700
Data Index: 4883284 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.9048. Min Act: -0.1700
Data Index: 5040810 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.7798. Min Act: -0.1700
Data Index: 29066 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.6548. Min Act: -0.1700
Data Index: 6450919 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.4673. Min Act: -0.1700
Data Index: 1563015 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.3423. Min Act: -0.1700
Data Index: 6080571 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.2798. Min Act: -0.1700
Data Index: 7064930 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.2798. Min Act: -0.1700
Data Index: 2573412 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.2798. Min Act: -0.1700
Data Index: 4807315 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.2173. Min Act: -0.1700
Data Index: 8720197 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.2173. Min Act: -0.1700
Data Index: 4494167 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.2173. Min Act: -0.1700
Data Index: 6711077 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.2173. Min Act: -0.1700
Data Index: 5810119 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.0923. Min Act: -0.1700
Data Index: 4863377 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.1548. Min Act: -0.1700
Data Index: 3832437 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.1548. Min Act: -0.1700
Data Index: 5823577 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.0923. Min Act: -0.1700
Data Index: 5010878 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.0923. Min Act: -0.1700
Data Index: 4255913 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.0610. Min Act: -0.1700
Data Index: 1707482 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1548. Min Range: -9.1548
Max Act: 8.0298. Min Act: -0.1700
Data Index: 951399 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19