Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 139 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0389. Min Range: -5.0389
Max Act: 5.0389. Min Act: -0.1700
Data Index: 5548440 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0389. Min Range: -5.0389
Max Act: 5.0389. Min Act: -0.1700
Data Index: 930681 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0389. Min Range: -5.0389
Max Act: 5.0389. Min Act: -0.1700
Data Index: 1023891 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0389. Min Range: -5.0389
Max Act: 5.0076. Min Act: -0.1700
Data Index: 4897519 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.9764. Min Act: -0.1700
Data Index: 2252579 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.9764. Min Act: -0.1699
Data Index: 2772419 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.9451. Min Act: -0.1700
Data Index: 161637 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.9451. Min Act: -0.1700
Data Index: 8688269 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.9139. Min Act: -0.1699
Data Index: 4642192 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.9139. Min Act: -0.1700
Data Index: 4075685 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.9139. Min Act: -0.1700
Data Index: 8555126 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.8826. Min Act: -0.1700
Data Index: 1803627 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.8826. Min Act: -0.1699
Data Index: 8639665 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.8514. Min Act: -0.1700
Data Index: 3781201 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.8826. Min Act: -0.1700
Data Index: 2300173 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.8514. Min Act: -0.1700
Data Index: 691533 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.8826. Min Act: -0.1700
Data Index: 4913364 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.8826. Min Act: -0.1700
Data Index: 8013117 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.8514. Min Act: -0.1700
Data Index: 5122060 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.8514. Min Act: -0.1700
Data Index: 5294906 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19