Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.8184. Min Act: -0.1700
Data Index: 6860635 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6934. Min Act: -0.1700
Data Index: 6651299 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6622. Min Act: -0.1700
Data Index: 3089057 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.5997. Min Act: -0.1700
Data Index: 3592370 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.5997. Min Act: -0.1700
Data Index: 1726902 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.5372. Min Act: -0.1700
Data Index: 7667584 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.5372. Min Act: -0.1700
Data Index: 5728133 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.5372. Min Act: -0.1700
Data Index: 2075445 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.5059. Min Act: -0.1700
Data Index: 921968 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.5059. Min Act: -0.1700
Data Index: 1367900 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.4747. Min Act: -0.1700
Data Index: 3696978 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.4747. Min Act: -0.1700
Data Index: 8533673 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.4747. Min Act: -0.1700
Data Index: 1123309 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.4434. Min Act: -0.1700
Data Index: 2143661 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.4434. Min Act: -0.1700
Data Index: 4444033 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.4434. Min Act: -0.1700
Data Index: 1694743 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.4122. Min Act: -0.1700
Data Index: 109633 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.4122. Min Act: -0.1700
Data Index: 596782 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.4122. Min Act: -0.1700
Data Index: 509310 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.4122. Min Act: -0.1700
Data Index: 1661067 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19