Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3075 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.9362. Min Act: -0.1700
Data Index: 6713544 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.8737. Min Act: -0.1700
Data Index: 6855821 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.7487. Min Act: -0.1700
Data Index: 6191865 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.6862. Min Act: -0.1700
Data Index: 5400854 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.5612. Min Act: -0.1700
Data Index: 247268 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.5299. Min Act: -0.1700
Data Index: 1373362 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.5299. Min Act: -0.1700
Data Index: 6248917 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.4987. Min Act: -0.1700
Data Index: 5388075 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.4674. Min Act: -0.1700
Data Index: 3807474 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.4049. Min Act: -0.1700
Data Index: 3807473 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.4049. Min Act: -0.1700
Data Index: 5844965 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.3737. Min Act: -0.1700
Data Index: 8182156 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.3737. Min Act: -0.1700
Data Index: 1156393 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.3112. Min Act: -0.1700
Data Index: 5536568 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.3424. Min Act: -0.1700
Data Index: 7701085 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.3424. Min Act: -0.1700
Data Index: 2572411 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.3112. Min Act: -0.1700
Data Index: 5828354 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.2799. Min Act: -0.1700
Data Index: 1409557 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.2799. Min Act: -0.1700
Data Index: 8203236 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9362. Min Range: -7.9362
Max Act: 7.2174. Min Act: -0.1700
Data Index: 6183413 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19