Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4302 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0767. Min Range: -8.0767
Max Act: 8.0767. Min Act: -0.1700
Data Index: 1159477 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.7642. Min Act: -0.1700
Data Index: 1159475 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.7642. Min Act: -0.1700
Data Index: 3730987 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.6704. Min Act: -0.1700
Data Index: 509568 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.6392. Min Act: -0.1700
Data Index: 5667193 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.6392. Min Act: -0.1700
Data Index: 5943411 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.5454. Min Act: -0.1700
Data Index: 6937618 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.5142. Min Act: -0.1700
Data Index: 1266840 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.4829. Min Act: -0.1700
Data Index: 3698930 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.5142. Min Act: -0.1700
Data Index: 3062178 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.4829. Min Act: -0.1700
Data Index: 2825922 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.4829. Min Act: -0.1700
Data Index: 3204759 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.4517. Min Act: -0.1700
Data Index: 8197230 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.4204. Min Act: -0.1700
Data Index: 8409628 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.3579. Min Act: -0.1700
Data Index: 228228 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.3267. Min Act: -0.1700
Data Index: 6549121 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.3267. Min Act: -0.1700
Data Index: 2092409 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.2954. Min Act: -0.1700
Data Index: 4360185 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.2954. Min Act: -0.1700
Data Index: 7855368 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0767. Min Range: -8.0767
Max Act: 7.3267. Min Act: -0.1700
Data Index: 2603115 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19