Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2907 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.3113. Min Act: -0.1700
Data Index: 8490254 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.2488. Min Act: -0.1700
Data Index: 7709206 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.2176. Min Act: -0.1700
Data Index: 6778495 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.2176. Min Act: -0.1700
Data Index: 3272976 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.1863. Min Act: -0.1700
Data Index: 585680 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.1863. Min Act: -0.1700
Data Index: 2274573 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0926. Min Act: -0.1700
Data Index: 4148110 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.1238. Min Act: -0.1700
Data Index: 585678 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.1238. Min Act: -0.1700
Data Index: 3791841 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0926. Min Act: -0.1700
Data Index: 4038527 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0613. Min Act: -0.1700
Data Index: 3658769 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0613. Min Act: -0.1700
Data Index: 8592615 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0613. Min Act: -0.1700
Data Index: 8111532 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0613. Min Act: -0.1700
Data Index: 7849504 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0301. Min Act: -0.1700
Data Index: 5182455 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0301. Min Act: -0.1700
Data Index: 1216302 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0613. Min Act: -0.1700
Data Index: 5004264 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.9988. Min Act: -0.1700
Data Index: 5242687 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0301. Min Act: -0.1700
Data Index: 4038528 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.9988. Min Act: -0.1700
Data Index: 8427897 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19