Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2954 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.6636. Min Act: -0.1700
Data Index: 6005922 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.5074. Min Act: -0.1700
Data Index: 3065358 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.5074. Min Act: -0.1700
Data Index: 7859361 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.4136. Min Act: -0.1700
Data Index: 3650523 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.4136. Min Act: -0.1700
Data Index: 8676434 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.3824. Min Act: -0.1700
Data Index: 6630551 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.3824. Min Act: -0.1700
Data Index: 5251556 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.3511. Min Act: -0.1700
Data Index: 1465645 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.2261. Min Act: -0.1700
Data Index: 6809766 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.1949. Min Act: -0.1700
Data Index: 1965618 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.1949. Min Act: -0.1700
Data Index: 7566424 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.1636. Min Act: -0.1700
Data Index: 7173201 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.1636. Min Act: -0.1700
Data Index: 7342104 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.1324. Min Act: -0.1700
Data Index: 1243708 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.1324. Min Act: -0.1700
Data Index: 6526706 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.0699. Min Act: -0.1700
Data Index: 1568271 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.1324. Min Act: -0.1700
Data Index: 1502701 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.1011. Min Act: -0.1700
Data Index: 8741843 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.1011. Min Act: -0.1700
Data Index: 3076759 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6636. Min Range: -6.6636
Max Act: 6.0699. Min Act: -0.1700
Data Index: 1976004 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19