Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.8506. Min Act: -0.1700
Data Index: 4795842 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.5068. Min Act: -0.1700
Data Index: 4197035 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.3818. Min Act: -0.1700
Data Index: 4703137 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.4443. Min Act: -0.1700
Data Index: 3947577 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.4131. Min Act: -0.1700
Data Index: 1729846 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.3506. Min Act: -0.1700
Data Index: 3606893 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.3193. Min Act: -0.1700
Data Index: 5741895 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.2568. Min Act: -0.1700
Data Index: 2812250 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.2568. Min Act: -0.1700
Data Index: 5263218 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.1631. Min Act: -0.1700
Data Index: 6011945 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.1631. Min Act: -0.1700
Data Index: 7610116 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.1318. Min Act: -0.1700
Data Index: 3597018 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.1318. Min Act: -0.1700
Data Index: 8282581 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.1318. Min Act: -0.1700
Data Index: 4795829 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.1006. Min Act: -0.1700
Data Index: 2304763 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.0693. Min Act: -0.1700
Data Index: 3597015 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.0381. Min Act: -0.1700
Data Index: 5335704 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.0068. Min Act: -0.1700
Data Index: 3393420 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.0068. Min Act: -0.1700
Data Index: 1529303 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8506. Min Range: -7.8506
Max Act: 7.0381. Min Act: -0.1700
Data Index: 549053 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19