Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 126 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.9081. Min Act: -0.1700
Data Index: 7005536 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.8740. Min Act: -0.1700
Data Index: 5474995 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.8569. Min Act: -0.1700
Data Index: 4728427 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.8397. Min Act: -0.1700
Data Index: 642244 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.8397. Min Act: -0.1700
Data Index: 2978345 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.8054. Min Act: -0.1700
Data Index: 115745 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.8312. Min Act: -0.1700
Data Index: 8032146 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.8140. Min Act: -0.1700
Data Index: 8095376 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.8140. Min Act: -0.1700
Data Index: 2724943 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.8140. Min Act: -0.1700
Data Index: 6397716 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.8054. Min Act: -0.1700
Data Index: 2380381 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.8140. Min Act: -0.1700
Data Index: 1672972 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.8054. Min Act: -0.1700
Data Index: 8544436 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.7796. Min Act: -0.1700
Data Index: 6108747 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.8054. Min Act: -0.1700
Data Index: 5312272 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.7882. Min Act: -0.1700
Data Index: 8009241 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.7882. Min Act: -0.1700
Data Index: 1166302 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.7709. Min Act: -0.1700
Data Index: 2686146 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.7796. Min Act: -0.1700
Data Index: 4671190 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9081. Min Range: -1.9081
Max Act: 1.7623. Min Act: -0.1700
Data Index: 4938768 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19