Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6164. Min Range: -8.6164
Max Act: 8.6164. Min Act: -0.1700
Data Index: 5278360 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6164. Min Range: -8.6164
Max Act: 8.4914. Min Act: -0.1700
Data Index: 7118929 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6164. Min Range: -8.6164
Max Act: 8.1164. Min Act: -0.1700
Data Index: 3035959 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6164. Min Range: -8.6164
Max Act: 8.0851. Min Act: -0.1700
Data Index: 1057644 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6164. Min Range: -8.6164
Max Act: 8.0851. Min Act: -0.1700
Data Index: 8064507 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.9914. Min Act: -0.1700
Data Index: 6471208 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.9914. Min Act: -0.1700
Data Index: 2575951 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.9601. Min Act: -0.1700
Data Index: 4919071 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.9601. Min Act: -0.1700
Data Index: 5118930 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.9289. Min Act: -0.1700
Data Index: 159878 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.8976. Min Act: -0.1700
Data Index: 3389320 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.9289. Min Act: -0.1700
Data Index: 8688217 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.8664. Min Act: -0.1700
Data Index: 1727357 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.8664. Min Act: -0.1700
Data Index: 892340 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.8351. Min Act: -0.1700
Data Index: 7026712 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.8039. Min Act: -0.1700
Data Index: 6659193 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.7726. Min Act: -0.1700
Data Index: 3373451 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.7414. Min Act: -0.1700
Data Index: 7499425 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.7414. Min Act: -0.1700
Data Index: 3592682 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6164. Min Range: -8.6164
Max Act: 7.7101. Min Act: -0.1700
Data Index: 6485853 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19