Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1045 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.2430. Min Act: -0.1700
Data Index: 4278990 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.1644. Min Act: -0.1700
Data Index: 5733746 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0383. Min Act: -0.1700
Data Index: 3885954 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0699. Min Act: -0.1700
Data Index: 7750880 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0383. Min Act: -0.1700
Data Index: 4519421 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0225. Min Act: -0.1700
Data Index: 3177091 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0067. Min Act: -0.1700
Data Index: 7291562 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0067. Min Act: -0.1700
Data Index: 3460197 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2430. Min Range: -3.2430
Max Act: 2.9909. Min Act: -0.1700
Data Index: 6266237 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2430. Min Range: -3.2430
Max Act: 3.0067. Min Act: -0.1700
Data Index: 6293454 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2430. Min Range: -3.2430
Max Act: 2.9909. Min Act: -0.1700
Data Index: 6445672 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2430. Min Range: -3.2430
Max Act: 2.9751. Min Act: -0.1700
Data Index: 5094988 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2430. Min Range: -3.2430
Max Act: 2.9751. Min Act: -0.1700
Data Index: 6601208 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2430. Min Range: -3.2430
Max Act: 2.9751. Min Act: -0.1700
Data Index: 1401484 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2430. Min Range: -3.2430
Max Act: 2.9751. Min Act: -0.1700
Data Index: 4472344 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2430. Min Range: -3.2430
Max Act: 2.9909. Min Act: -0.1700
Data Index: 8519569 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2430. Min Range: -3.2430
Max Act: 2.9593. Min Act: -0.1700
Data Index: 5329157 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2430. Min Range: -3.2430
Max Act: 2.9276. Min Act: -0.1700
Data Index: 213707 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2430. Min Range: -3.2430
Max Act: 2.9751. Min Act: -0.1700
Data Index: 491427 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2430. Min Range: -3.2430
Max Act: 2.9435. Min Act: -0.1700
Data Index: 5733747 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19