Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 671 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.7142. Min Act: -0.1700
Data Index: 4867082 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.5892. Min Act: -0.1700
Data Index: 731085 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.5892. Min Act: -0.1700
Data Index: 2156292 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.4955. Min Act: -0.1700
Data Index: 5499920 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.4955. Min Act: -0.1700
Data Index: 153127 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.4642. Min Act: -0.1700
Data Index: 8647309 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.4642. Min Act: -0.1700
Data Index: 768721 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.4330. Min Act: -0.1700
Data Index: 6232368 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.4017. Min Act: -0.1700
Data Index: 2292357 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.4017. Min Act: -0.1700
Data Index: 4397563 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.3080. Min Act: -0.1700
Data Index: 5516601 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.3392. Min Act: -0.1700
Data Index: 7275205 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.3080. Min Act: -0.1700
Data Index: 2493631 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.3080. Min Act: -0.1700
Data Index: 2145086 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.3080. Min Act: -0.1700
Data Index: 5383306 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.3080. Min Act: -0.1700
Data Index: 8815334 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.3080. Min Act: -0.1700
Data Index: 5796259 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.3080. Min Act: -0.1700
Data Index: 5064236 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.2767. Min Act: -0.1700
Data Index: 4991070 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7142. Min Range: -6.7142
Max Act: 6.2767. Min Act: -0.1700
Data Index: 3519800 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19