Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3053 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0728. Min Range: -5.0728
Max Act: 5.0728. Min Act: -0.1700
Data Index: 7155148 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0728. Min Range: -5.0728
Max Act: 5.0103. Min Act: -0.1700
Data Index: 7659332 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0728. Min Range: -5.0728
Max Act: 5.0103. Min Act: -0.1700
Data Index: 3566810 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.9791. Min Act: -0.1700
Data Index: 7813740 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.9478. Min Act: -0.1700
Data Index: 5529586 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.9478. Min Act: -0.1700
Data Index: 32363 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.8853. Min Act: -0.1700
Data Index: 4712230 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.9166. Min Act: -0.1700
Data Index: 6469129 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.8541. Min Act: -0.1700
Data Index: 6194886 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.8853. Min Act: -0.1700
Data Index: 7439188 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.8541. Min Act: -0.1700
Data Index: 7517815 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.8541. Min Act: -0.1700
Data Index: 5699825 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.8541. Min Act: -0.1700
Data Index: 5322666 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.8541. Min Act: -0.1700
Data Index: 4340991 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.8228. Min Act: -0.1700
Data Index: 381299 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.8541. Min Act: -0.1700
Data Index: 3504084 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.8541. Min Act: -0.1700
Data Index: 1568112 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.8541. Min Act: -0.1700
Data Index: 5988301 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.8228. Min Act: -0.1700
Data Index: 5335845 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0728. Min Range: -5.0728
Max Act: 4.8228. Min Act: -0.1700
Data Index: 2455704 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19