Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 327 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5118. Min Range: -6.5118
Max Act: 6.5118. Min Act: -0.1700
Data Index: 8206494 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.9493. Min Act: -0.1700
Data Index: 1272430 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.9181. Min Act: -0.1700
Data Index: 7644426 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.9181. Min Act: -0.1700
Data Index: 7224523 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.9493. Min Act: -0.1700
Data Index: 2984277 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.8868. Min Act: -0.1700
Data Index: 5132285 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.8868. Min Act: -0.1700
Data Index: 4553169 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.8556. Min Act: -0.1700
Data Index: 5804625 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.7931. Min Act: -0.1700
Data Index: 4890539 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.7931. Min Act: -0.1700
Data Index: 5746884 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.7306. Min Act: -0.1700
Data Index: 6966294 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.7306. Min Act: -0.1700
Data Index: 7644425 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.7306. Min Act: -0.1700
Data Index: 3127967 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.7306. Min Act: -0.1700
Data Index: 8396605 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.6681. Min Act: -0.1700
Data Index: 5715320 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.6993. Min Act: -0.1700
Data Index: 3827886 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.6368. Min Act: -0.1700
Data Index: 5237104 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.6681. Min Act: -0.1700
Data Index: 2065788 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.6993. Min Act: -0.1700
Data Index: 2201628 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5118. Min Range: -6.5118
Max Act: 5.6368. Min Act: -0.1700
Data Index: 1984189 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19