Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 777 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.1518. Min Act: -0.1700
Data Index: 470922 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.0682. Min Act: -0.1700
Data Index: 4872163 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.0682. Min Act: -0.1700
Data Index: 470920 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.0682. Min Act: -0.1700
Data Index: 6019577 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.0514. Min Act: -0.1700
Data Index: 3271255 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.0345. Min Act: -0.1700
Data Index: 5450754 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.0514. Min Act: -0.1700
Data Index: 4583474 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.0345. Min Act: -0.1700
Data Index: 2370815 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.0008. Min Act: -0.1700
Data Index: 6669020 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.0177. Min Act: -0.1700
Data Index: 7247298 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.0177. Min Act: -0.1700
Data Index: 5113597 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.0345. Min Act: -0.1700
Data Index: 5043513 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.0177. Min Act: -0.1700
Data Index: 4991622 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1518. Min Range: -2.1518
Max Act: 2.0008. Min Act: -0.1700
Data Index: 1369642 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1518. Min Range: -2.1518
Max Act: 1.9669. Min Act: -0.1700
Data Index: 1435684 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1518. Min Range: -2.1518
Max Act: 1.9839. Min Act: -0.1700
Data Index: 5083424 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1518. Min Range: -2.1518
Max Act: 1.9669. Min Act: -0.1700
Data Index: 782317 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1518. Min Range: -2.1518
Max Act: 1.9669. Min Act: -0.1700
Data Index: 2761082 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1518. Min Range: -2.1518
Max Act: 1.9669. Min Act: -0.1700
Data Index: 4618604 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1518. Min Range: -2.1518
Max Act: 1.9839. Min Act: -0.1700
Data Index: 1680759 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19