Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2582 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.6975. Min Act: -0.1700
Data Index: 2152600 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.6334. Min Act: -0.1700
Data Index: 7150404 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.6012. Min Act: -0.1700
Data Index: 8474211 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.6012. Min Act: -0.1700
Data Index: 212883 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.5690. Min Act: -0.1700
Data Index: 5212817 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.5205. Min Act: -0.1700
Data Index: 4055632 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.5205. Min Act: -0.1700
Data Index: 259149 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.5043. Min Act: -0.1700
Data Index: 4398656 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.5043. Min Act: -0.1700
Data Index: 1920869 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.4881. Min Act: -0.1700
Data Index: 4933414 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.4881. Min Act: -0.1700
Data Index: 1271354 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.4881. Min Act: -0.1700
Data Index: 5553225 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.4881. Min Act: -0.1700
Data Index: 493108 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.4881. Min Act: -0.1700
Data Index: 3581440 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.4557. Min Act: -0.1700
Data Index: 5529659 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.4881. Min Act: -0.1700
Data Index: 1370987 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.4719. Min Act: -0.1700
Data Index: 7739211 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.4719. Min Act: -0.1700
Data Index: 4055063 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.4719. Min Act: -0.1700
Data Index: 6216077 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6975. Min Range: -2.6975
Max Act: 2.4557. Min Act: -0.1700
Data Index: 5699341 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19