Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1887 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.5498. Min Act: -0.1700
Data Index: 1747361 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.5498. Min Act: -0.1700
Data Index: 603997 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.4872. Min Act: -0.1700
Data Index: 603996 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.4872. Min Act: -0.1700
Data Index: 247156 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.4872. Min Act: -0.1700
Data Index: 247136 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.4558. Min Act: -0.1700
Data Index: 6855982 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.4558. Min Act: -0.1700
Data Index: 4146940 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.4245. Min Act: -0.1700
Data Index: 284692 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.3931. Min Act: -0.1700
Data Index: 3389332 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.3618. Min Act: -0.1700
Data Index: 1525124 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.3461. Min Act: -0.1700
Data Index: 7289572 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.3618. Min Act: -0.1700
Data Index: 3946742 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.3774. Min Act: -0.1700
Data Index: 3836169 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.3618. Min Act: -0.1700
Data Index: 247155 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.3461. Min Act: -0.1700
Data Index: 3355117 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.3304. Min Act: -0.1700
Data Index: 9487 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.2990. Min Act: -0.1700
Data Index: 6175974 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.2833. Min Act: -0.1700
Data Index: 5335993 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.2990. Min Act: -0.1700
Data Index: 5851332 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.2833. Min Act: -0.1700
Data Index: 4839178 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19