Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1876 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.2770. Min Act: -0.1700
Data Index: 5041841 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.2770. Min Act: -0.1700
Data Index: 8663643 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.0582. Min Act: -0.1700
Data Index: 4350709 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9957. Min Act: -0.1700
Data Index: 4649261 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9332. Min Act: -0.1700
Data Index: 4832834 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.8707. Min Act: -0.1700
Data Index: 4505289 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.8395. Min Act: -0.1700
Data Index: 4123522 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.8395. Min Act: -0.1700
Data Index: 5133958 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.7457. Min Act: -0.1700
Data Index: 1794972 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6832. Min Act: -0.1700
Data Index: 4704750 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.7145. Min Act: -0.1700
Data Index: 3141749 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6832. Min Act: -0.1700
Data Index: 3562646 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6832. Min Act: -0.1700
Data Index: 1511536 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6520. Min Act: -0.1700
Data Index: 5209143 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6520. Min Act: -0.1700
Data Index: 8801812 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6832. Min Act: -0.1700
Data Index: 7542263 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6520. Min Act: -0.1700
Data Index: 4619294 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6207. Min Act: -0.1700
Data Index: 8113335 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.5895. Min Act: -0.1700
Data Index: 6843044 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.5895. Min Act: -0.1700
Data Index: 8012801 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19