Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1306 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.4890. Min Act: -0.1700
Data Index: 5829945 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.4728. Min Act: -0.1700
Data Index: 6102671 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.4240. Min Act: -0.1700
Data Index: 5207410 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.4240. Min Act: -0.1700
Data Index: 4409706 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.4240. Min Act: -0.1700
Data Index: 4024132 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.3914. Min Act: -0.1700
Data Index: 2054818 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.4077. Min Act: -0.1700
Data Index: 4394856 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.3914. Min Act: -0.1700
Data Index: 3847309 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.3914. Min Act: -0.1700
Data Index: 3693280 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.4077. Min Act: -0.1700
Data Index: 841676 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.3587. Min Act: -0.1700
Data Index: 600941 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.3751. Min Act: -0.1700
Data Index: 214661 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.3423. Min Act: -0.1700
Data Index: 2012774 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.3587. Min Act: -0.1700
Data Index: 6979794 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.3587. Min Act: -0.1700
Data Index: 3739772 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1789934 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.3423. Min Act: -0.1700
Data Index: 667788 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.3587. Min Act: -0.1700
Data Index: 2581888 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.3423. Min Act: -0.1700
Data Index: 1178712 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4890. Min Range: -2.4890
Max Act: 2.3587. Min Act: -0.1700
Data Index: 1688747 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19