Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4857 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0686. Min Range: -5.0686
Max Act: 5.0686. Min Act: -0.1700
Data Index: 6047999 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0686. Min Range: -5.0686
Max Act: 5.0373. Min Act: -0.1700
Data Index: 4988334 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0686. Min Range: -5.0686
Max Act: 5.0061. Min Act: -0.1700
Data Index: 7237264 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0686. Min Range: -5.0686
Max Act: 5.0061. Min Act: -0.1700
Data Index: 2663402 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.9436. Min Act: -0.1700
Data Index: 3130830 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.9123. Min Act: -0.1700
Data Index: 2040458 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.9123. Min Act: -0.1700
Data Index: 7998164 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.9123. Min Act: -0.1700
Data Index: 1963882 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.8811. Min Act: -0.1700
Data Index: 1963889 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.8811. Min Act: -0.1700
Data Index: 8633619 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.8811. Min Act: -0.1700
Data Index: 1170523 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.8498. Min Act: -0.1700
Data Index: 6063892 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.8498. Min Act: -0.1700
Data Index: 1016616 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.8498. Min Act: -0.1700
Data Index: 4791115 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.8186. Min Act: -0.1700
Data Index: 4342868 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.8186. Min Act: -0.1700
Data Index: 2927303 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.8186. Min Act: -0.1700
Data Index: 4220761 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.8186. Min Act: -0.1700
Data Index: 8008239 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.8498. Min Act: -0.1700
Data Index: 8399697 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0686. Min Range: -5.0686
Max Act: 4.8186. Min Act: -0.1700
Data Index: 1366610 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19