Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4606 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2987. Min Range: -7.2987
Max Act: 7.2987. Min Act: -0.1700
Data Index: 4510917 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2987. Min Range: -7.2987
Max Act: 7.2362. Min Act: -0.1700
Data Index: 398296 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2987. Min Range: -7.2987
Max Act: 7.1737. Min Act: -0.1700
Data Index: 5270073 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2987. Min Range: -7.2987
Max Act: 7.1424. Min Act: -0.1700
Data Index: 3172302 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2987. Min Range: -7.2987
Max Act: 7.0487. Min Act: -0.1700
Data Index: 5008440 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2987. Min Range: -7.2987
Max Act: 7.0174. Min Act: -0.1700
Data Index: 613748 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.9549. Min Act: -0.1700
Data Index: 4269663 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.9862. Min Act: -0.1700
Data Index: 5889317 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.9237. Min Act: -0.1700
Data Index: 7962652 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.8299. Min Act: -0.1700
Data Index: 3068801 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.8299. Min Act: -0.1700
Data Index: 211568 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.8612. Min Act: -0.1700
Data Index: 8368670 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.8299. Min Act: -0.1700
Data Index: 8255415 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.8299. Min Act: -0.1700
Data Index: 1530872 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.7987. Min Act: -0.1700
Data Index: 5994919 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.7987. Min Act: -0.1700
Data Index: 1199708 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.7987. Min Act: -0.1700
Data Index: 6419319 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.7987. Min Act: -0.1700
Data Index: 8622260 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.7987. Min Act: -0.1700
Data Index: 6283724 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2987. Min Range: -7.2987
Max Act: 6.7674. Min Act: -0.1700
Data Index: 7559631 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19