Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3594 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6302. Min Range: -7.6302
Max Act: 7.6302. Min Act: -0.1700
Data Index: 8116643 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6302. Min Range: -7.6302
Max Act: 7.3490. Min Act: -0.1700
Data Index: 4502291 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6302. Min Range: -7.6302
Max Act: 7.3177. Min Act: -0.1700
Data Index: 6366099 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6302. Min Range: -7.6302
Max Act: 7.2240. Min Act: -0.1700
Data Index: 6455970 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6302. Min Range: -7.6302
Max Act: 7.1927. Min Act: -0.1700
Data Index: 5236544 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6302. Min Range: -7.6302
Max Act: 7.1615. Min Act: -0.1700
Data Index: 8563994 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6302. Min Range: -7.6302
Max Act: 7.0990. Min Act: -0.1700
Data Index: 8226622 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6302. Min Range: -7.6302
Max Act: 7.0677. Min Act: -0.1700
Data Index: 492206 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6302. Min Range: -7.6302
Max Act: 7.0365. Min Act: -0.1700
Data Index: 6850754 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6302. Min Range: -7.6302
Max Act: 7.0052. Min Act: -0.1700
Data Index: 3077015 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6302. Min Range: -7.6302
Max Act: 7.0365. Min Act: -0.1700
Data Index: 5720491 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6302. Min Range: -7.6302
Max Act: 7.0052. Min Act: -0.1700
Data Index: 5285082 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6302. Min Range: -7.6302
Max Act: 6.9740. Min Act: -0.1700
Data Index: 4066546 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6302. Min Range: -7.6302
Max Act: 6.9427. Min Act: -0.1700
Data Index: 1782562 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6302. Min Range: -7.6302
Max Act: 6.9427. Min Act: -0.1700
Data Index: 3869707 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6302. Min Range: -7.6302
Max Act: 6.9427. Min Act: -0.1700
Data Index: 5799673 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6302. Min Range: -7.6302
Max Act: 6.9427. Min Act: -0.1700
Data Index: 7892938 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6302. Min Range: -7.6302
Max Act: 6.8802. Min Act: -0.1700
Data Index: 7523958 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6302. Min Range: -7.6302
Max Act: 6.8802. Min Act: -0.1700
Data Index: 25412 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6302. Min Range: -7.6302
Max Act: 6.9115. Min Act: -0.1700
Data Index: 7492836 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19