Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2118 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.7724. Min Act: -0.1700
Data Index: 6826003 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.7412. Min Act: -0.1700
Data Index: 4992911 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.7099. Min Act: -0.1700
Data Index: 8219139 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.5537. Min Act: -0.1700
Data Index: 5098463 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.4912. Min Act: -0.1700
Data Index: 1951188 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.4599. Min Act: -0.1700
Data Index: 5197822 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.4287. Min Act: -0.1700
Data Index: 4737056 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.3662. Min Act: -0.1700
Data Index: 6826010 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.3349. Min Act: -0.1700
Data Index: 273942 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.3349. Min Act: -0.1700
Data Index: 4411706 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.3037. Min Act: -0.1700
Data Index: 6324520 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.3349. Min Act: -0.1700
Data Index: 8025193 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.3037. Min Act: -0.1700
Data Index: 148059 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.3037. Min Act: -0.1700
Data Index: 6694236 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.3037. Min Act: -0.1700
Data Index: 6482537 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.3037. Min Act: -0.1700
Data Index: 1951189 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.2724. Min Act: -0.1700
Data Index: 7790011 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.2724. Min Act: -0.1700
Data Index: 3456742 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.2724. Min Act: -0.1700
Data Index: 6854011 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7724. Min Range: -5.7724
Max Act: 5.2724. Min Act: -0.1700
Data Index: 3853888 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19