Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4047 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.7268. Min Act: -0.1700
Data Index: 4373883 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.4768. Min Act: -0.1700
Data Index: 2277828 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.4768. Min Act: -0.1700
Data Index: 4736502 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.4143. Min Act: -0.1700
Data Index: 5581016 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.3518. Min Act: -0.1700
Data Index: 449869 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.1643. Min Act: -0.1700
Data Index: 5682632 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.1018. Min Act: -0.1700
Data Index: 3618309 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.1018. Min Act: -0.1700
Data Index: 8363226 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.0393. Min Act: -0.1700
Data Index: 7306246 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.1018. Min Act: -0.1700
Data Index: 7142338 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.0393. Min Act: -0.1700
Data Index: 4055474 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.0393. Min Act: -0.1700
Data Index: 4856284 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.0393. Min Act: -0.1700
Data Index: 5670564 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7268. Min Range: -9.7268
Max Act: 9.0393. Min Act: -0.1700
Data Index: 3404055 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7268. Min Range: -9.7268
Max Act: 8.9768. Min Act: -0.1700
Data Index: 7665260 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7268. Min Range: -9.7268
Max Act: 8.9768. Min Act: -0.1700
Data Index: 3781402 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7268. Min Range: -9.7268
Max Act: 8.9143. Min Act: -0.1700
Data Index: 4206156 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7268. Min Range: -9.7268
Max Act: 8.9143. Min Act: -0.1700
Data Index: 526323 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7268. Min Range: -9.7268
Max Act: 8.9143. Min Act: -0.1700
Data Index: 7035925 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7268. Min Range: -9.7268
Max Act: 8.9143. Min Act: -0.1700
Data Index: 1442803 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19