Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.4716. Min Act: -0.1700
Data Index: 366868 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.3778. Min Act: -0.1700
Data Index: 7201778 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.2841. Min Act: -0.1700
Data Index: 6934312 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.2528. Min Act: -0.1700
Data Index: 5099896 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.2216. Min Act: -0.1700
Data Index: 295805 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.2216. Min Act: -0.1700
Data Index: 7996799 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.2216. Min Act: -0.1700
Data Index: 6097620 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.1591. Min Act: -0.1700
Data Index: 957916 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.1278. Min Act: -0.1700
Data Index: 1548033 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.1278. Min Act: -0.1700
Data Index: 5635369 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.0966. Min Act: -0.1700
Data Index: 1774070 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.0341. Min Act: -0.1700
Data Index: 3095094 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.0341. Min Act: -0.1700
Data Index: 1593675 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.0028. Min Act: -0.1700
Data Index: 7763601 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.0028. Min Act: -0.1700
Data Index: 6840796 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.0028. Min Act: -0.1700
Data Index: 7202454 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.0028. Min Act: -0.1700
Data Index: 1173469 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.0028. Min Act: -0.1700
Data Index: 8811457 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.0028. Min Act: -0.1700
Data Index: 8313442 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4716. Min Range: -6.4716
Max Act: 6.0028. Min Act: -0.1700
Data Index: 3263916 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19