Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3821 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2114. Min Range: -8.2114
Max Act: 8.2114. Min Act: -0.1700
Data Index: 2884007 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2114. Min Range: -8.2114
Max Act: 8.0239. Min Act: -0.1700
Data Index: 3403116 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.9614. Min Act: -0.1700
Data Index: 6237790 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.8364. Min Act: -0.1700
Data Index: 7377695 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.8364. Min Act: -0.1700
Data Index: 7248580 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7739. Min Act: -0.1700
Data Index: 6753222 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7739. Min Act: -0.1700
Data Index: 1815755 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7739. Min Act: -0.1700
Data Index: 2614669 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7114. Min Act: -0.1700
Data Index: 2129892 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7739. Min Act: -0.1700
Data Index: 3114470 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7739. Min Act: -0.1700
Data Index: 898765 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7114. Min Act: -0.1700
Data Index: 2743351 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7114. Min Act: -0.1700
Data Index: 6347606 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7114. Min Act: -0.1700
Data Index: 1224271 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7114. Min Act: -0.1700
Data Index: 4482667 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7114. Min Act: -0.1700
Data Index: 4042279 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7114. Min Act: -0.1700
Data Index: 4062752 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7739. Min Act: -0.1700
Data Index: 2990165 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.6489. Min Act: -0.1700
Data Index: 5710945 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2114. Min Range: -8.2114
Max Act: 7.7114. Min Act: -0.1700
Data Index: 2125150 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19