Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1096 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.5700. Min Act: -0.1700
Data Index: 120227 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.5700. Min Act: -0.1700
Data Index: 2808320 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.5388. Min Act: -0.1700
Data Index: 3654551 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.5388. Min Act: -0.1700
Data Index: 6058287 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.4138. Min Act: -0.1700
Data Index: 945357 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.2575. Min Act: -0.1700
Data Index: 6000218 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.2888. Min Act: -0.1700
Data Index: 2984566 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.2888. Min Act: -0.1700
Data Index: 2322 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.2575. Min Act: -0.1700
Data Index: 1002228 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.2575. Min Act: -0.1700
Data Index: 2654839 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.2888. Min Act: -0.1700
Data Index: 3566550 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.2575. Min Act: -0.1700
Data Index: 2633318 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.2575. Min Act: -0.1700
Data Index: 1672480 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.1950. Min Act: -0.1700
Data Index: 8359686 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.1950. Min Act: -0.1700
Data Index: 4474929 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.1950. Min Act: -0.1700
Data Index: 5142763 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.1638. Min Act: -0.1700
Data Index: 6030006 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.1638. Min Act: -0.1700
Data Index: 2837556 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.1013. Min Act: -0.1700
Data Index: 1482044 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5700. Min Range: -6.5700
Max Act: 6.1013. Min Act: -0.1700
Data Index: 6510886 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19