Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1433 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.3424. Min Act: -0.1700
Data Index: 422947 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.3267. Min Act: -0.1700
Data Index: 1043084 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.3110. Min Act: -0.1700
Data Index: 4722448 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.3110. Min Act: -0.1700
Data Index: 5210595 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.2796. Min Act: -0.1700
Data Index: 4512276 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.2796. Min Act: -0.1700
Data Index: 8546209 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.2639. Min Act: -0.1700
Data Index: 2895641 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.2168. Min Act: -0.1700
Data Index: 1506885 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.2168. Min Act: -0.1700
Data Index: 3695762 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.2325. Min Act: -0.1700
Data Index: 2875387 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.2325. Min Act: -0.1700
Data Index: 8298263 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.2011. Min Act: -0.1700
Data Index: 5223899 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.2011. Min Act: -0.1700
Data Index: 6529674 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.2011. Min Act: -0.1700
Data Index: 7170643 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.1853. Min Act: -0.1700
Data Index: 182957 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.1853. Min Act: -0.1700
Data Index: 6629954 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.1539. Min Act: -0.1700
Data Index: 4277083 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.1696. Min Act: -0.1700
Data Index: 5297489 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.1696. Min Act: -0.1700
Data Index: 5134800 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3424. Min Range: -3.3424
Max Act: 3.1539. Min Act: -0.1700
Data Index: 4054850 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19