Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3046 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0847. Min Range: -5.0847
Max Act: 5.0847. Min Act: -0.1700
Data Index: 8111589 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0847. Min Range: -5.0847
Max Act: 5.0847. Min Act: -0.1700
Data Index: 3502685 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.9597. Min Act: -0.1700
Data Index: 4133200 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.9597. Min Act: -0.1700
Data Index: 5146484 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.8659. Min Act: -0.1700
Data Index: 6671508 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.8659. Min Act: -0.1700
Data Index: 681632 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.8347. Min Act: -0.1700
Data Index: 8794466 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.8034. Min Act: -0.1700
Data Index: 2198631 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.8034. Min Act: -0.1700
Data Index: 2966415 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.8034. Min Act: -0.1700
Data Index: 4187451 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.7722. Min Act: -0.1700
Data Index: 6751084 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.7722. Min Act: -0.1700
Data Index: 1597466 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.7722. Min Act: -0.1700
Data Index: 7508414 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.7409. Min Act: -0.1700
Data Index: 6641621 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.7097. Min Act: -0.1700
Data Index: 2198633 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.7097. Min Act: -0.1700
Data Index: 8041543 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.7097. Min Act: -0.1700
Data Index: 3516208 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.6784. Min Act: -0.1700
Data Index: 7031500 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.6472. Min Act: -0.1700
Data Index: 1299677 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0847. Min Range: -5.0847
Max Act: 4.6472. Min Act: -0.1700
Data Index: 1409597 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19