Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2854 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.8810. Min Act: -0.1700
Data Index: 7645494 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.8497. Min Act: -0.1700
Data Index: 5533501 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.8497. Min Act: -0.1700
Data Index: 8322233 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.8185. Min Act: -0.1700
Data Index: 460587 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.8185. Min Act: -0.1700
Data Index: 5353037 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.5685. Min Act: -0.1700
Data Index: 5985121 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.5060. Min Act: -0.1700
Data Index: 7918590 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.5060. Min Act: -0.1700
Data Index: 655798 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.5060. Min Act: -0.1700
Data Index: 4437933 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.5372. Min Act: -0.1700
Data Index: 1953762 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.4435. Min Act: -0.1700
Data Index: 3013131 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.4122. Min Act: -0.1700
Data Index: 5116678 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.4747. Min Act: -0.1700
Data Index: 2654892 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.4435. Min Act: -0.1700
Data Index: 2805569 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.4435. Min Act: -0.1700
Data Index: 8822666 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.4122. Min Act: -0.1700
Data Index: 8319553 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.4122. Min Act: -0.1700
Data Index: 6881268 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.3497. Min Act: -0.1700
Data Index: 3757065 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.3810. Min Act: -0.1700
Data Index: 507036 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8810. Min Range: -5.8810
Max Act: 5.3810. Min Act: -0.1700
Data Index: 4312947 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19