Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2402 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.8962. Min Act: -0.1700
Data Index: 3758908 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.8337. Min Act: -0.1700
Data Index: 6748549 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.7087. Min Act: -0.1700
Data Index: 396663 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.6462. Min Act: -0.1700
Data Index: 5734281 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.6150. Min Act: -0.1700
Data Index: 3251951 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.5837. Min Act: -0.1700
Data Index: 1609876 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.5525. Min Act: -0.1700
Data Index: 497162 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.4900. Min Act: -0.1700
Data Index: 7896090 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.4900. Min Act: -0.1700
Data Index: 7519276 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.4900. Min Act: -0.1700
Data Index: 8791177 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.4900. Min Act: -0.1700
Data Index: 4586247 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.4587. Min Act: -0.1700
Data Index: 2457237 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.4275. Min Act: -0.1700
Data Index: 4358882 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.4275. Min Act: -0.1700
Data Index: 5915957 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.4275. Min Act: -0.1700
Data Index: 1688584 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.3962. Min Act: -0.1700
Data Index: 6611966 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.3962. Min Act: -0.1700
Data Index: 4367159 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.3650. Min Act: -0.1700
Data Index: 5095604 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.3650. Min Act: -0.1700
Data Index: 4392292 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8962. Min Range: -5.8962
Max Act: 5.3650. Min Act: -0.1700
Data Index: 2550214 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19