Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6195 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.5198. Min Act: -0.1700
Data Index: 986506 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.4573. Min Act: -0.1700
Data Index: 4463826 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.4573. Min Act: -0.1698
Data Index: 3992132 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.4261. Min Act: -0.1700
Data Index: 5478129 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.3948. Min Act: -0.1700
Data Index: 4830356 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.3636. Min Act: -0.1700
Data Index: 2509023 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.3011. Min Act: -0.1700
Data Index: 2612174 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.2698. Min Act: -0.1700
Data Index: 4960696 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.2386. Min Act: -0.1700
Data Index: 1604878 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.2698. Min Act: -0.1700
Data Index: 5372162 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.2698. Min Act: -0.1700
Data Index: 6789217 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.2386. Min Act: -0.1700
Data Index: 7092 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.2386. Min Act: -0.1700
Data Index: 6997493 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.2073. Min Act: -0.1700
Data Index: 6914161 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.2073. Min Act: -0.1700
Data Index: 5403200 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.2073. Min Act: -0.1700
Data Index: 6371570 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.2073. Min Act: -0.1700
Data Index: 1425845 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.1761. Min Act: -0.1700
Data Index: 8132755 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.1761. Min Act: -0.1700
Data Index: 7350156 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5198. Min Range: -6.5198
Max Act: 6.1761. Min Act: -0.1700
Data Index: 1702273 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19