Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1908 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.8063. Min Act: -0.1700
Data Index: 1151271 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.7265. Min Act: -0.1700
Data Index: 2681305 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.6465. Min Act: -0.1700
Data Index: 5241498 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.6465. Min Act: -0.1700
Data Index: 8283474 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.6304. Min Act: -0.1700
Data Index: 6884669 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.5982. Min Act: -0.1700
Data Index: 7401296 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.6304. Min Act: -0.1700
Data Index: 4202793 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.6143. Min Act: -0.1700
Data Index: 6355567 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.5821. Min Act: -0.1700
Data Index: 8118747 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.6143. Min Act: -0.1700
Data Index: 4968958 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.5982. Min Act: -0.1700
Data Index: 8465028 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.5982. Min Act: -0.1700
Data Index: 6037147 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.5821. Min Act: -0.1700
Data Index: 801491 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.6143. Min Act: -0.1700
Data Index: 4620991 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.5821. Min Act: -0.1700
Data Index: 5762336 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.5821. Min Act: -0.1700
Data Index: 3300664 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.5821. Min Act: -0.1700
Data Index: 7154449 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.5660. Min Act: -0.1700
Data Index: 5932502 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.5660. Min Act: -0.1700
Data Index: 5851646 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8063. Min Range: -2.8063
Max Act: 2.5821. Min Act: -0.1700
Data Index: 4707545 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19