Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2652 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.8660. Min Act: -0.1700
Data Index: 1022395 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.6160. Min Act: -0.1700
Data Index: 50481 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.5847. Min Act: -0.1700
Data Index: 2620779 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.5535. Min Act: -0.1700
Data Index: 1558217 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.5222. Min Act: -0.1700
Data Index: 7961158 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.3972. Min Act: -0.1700
Data Index: 2014889 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.3972. Min Act: -0.1700
Data Index: 6590467 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.3660. Min Act: -0.1700
Data Index: 6886617 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.3972. Min Act: -0.1700
Data Index: 5222783 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.3660. Min Act: -0.1700
Data Index: 3479836 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.2722. Min Act: -0.1700
Data Index: 7610448 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.3035. Min Act: -0.1700
Data Index: 2137914 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.2722. Min Act: -0.1700
Data Index: 4592947 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.3035. Min Act: -0.1700
Data Index: 7430078 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.3035. Min Act: -0.1700
Data Index: 7354036 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.3035. Min Act: -0.1700
Data Index: 7200623 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.2722. Min Act: -0.1700
Data Index: 2815514 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.2722. Min Act: -0.1700
Data Index: 4480596 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.2410. Min Act: -0.1700
Data Index: 6219121 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8660. Min Range: -5.8660
Max Act: 5.2410. Min Act: -0.1700
Data Index: 5462619 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19