Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 914 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2170. Min Range: -4.2170
Max Act: 4.2170. Min Act: -0.1700
Data Index: 6130804 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2170. Min Range: -4.2170
Max Act: 4.0607. Min Act: -0.1700
Data Index: 2991067 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2170. Min Range: -4.2170
Max Act: 4.0607. Min Act: -0.1700
Data Index: 7155387 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.9670. Min Act: -0.1700
Data Index: 5854139 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.8732. Min Act: -0.1700
Data Index: 3503569 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.8732. Min Act: -0.1700
Data Index: 5915162 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.8732. Min Act: -0.1700
Data Index: 7905563 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.8106. Min Act: -0.1700
Data Index: 6860627 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.7794. Min Act: -0.1700
Data Index: 3244689 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.7794. Min Act: -0.1700
Data Index: 4076348 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.7481. Min Act: -0.1700
Data Index: 284388 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.7481. Min Act: -0.1700
Data Index: 8531558 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.7481. Min Act: -0.1700
Data Index: 98215 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.7168. Min Act: -0.1700
Data Index: 2828336 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.7168. Min Act: -0.1700
Data Index: 2671413 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.7168. Min Act: -0.1700
Data Index: 4655983 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.7168. Min Act: -0.1700
Data Index: 3350022 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.6855. Min Act: -0.1700
Data Index: 7512284 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.6855. Min Act: -0.1700
Data Index: 4935698 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2170. Min Range: -4.2170
Max Act: 3.6855. Min Act: -0.1700
Data Index: 6656698 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19