Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1136 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.9855. Min Act: -0.1700
Data Index: 7196952 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.9230. Min Act: -0.1700
Data Index: 7196950 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.9855. Min Act: -0.1700
Data Index: 7196951 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.9230. Min Act: -0.1700
Data Index: 7074797 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.7980. Min Act: -0.1700
Data Index: 4207128 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.7980. Min Act: -0.1700
Data Index: 1166173 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.7980. Min Act: -0.1700
Data Index: 1167325 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.7355. Min Act: -0.1700
Data Index: 2726335 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.6730. Min Act: -0.1700
Data Index: 5046869 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.6730. Min Act: -0.1700
Data Index: 8470499 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.5480. Min Act: -0.1700
Data Index: 7677236 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.4230. Min Act: -0.1700
Data Index: 4014499 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.4230. Min Act: -0.1700
Data Index: 5953188 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.4230. Min Act: -0.1700
Data Index: 4259782 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.3605. Min Act: -0.1700
Data Index: 1306414 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.3605. Min Act: -0.1700
Data Index: 8426081 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.3605. Min Act: -0.1700
Data Index: 1955048 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.3605. Min Act: -0.1700
Data Index: 8016854 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.2980. Min Act: -0.1700
Data Index: 557037 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9855. Min Range: -8.9855
Max Act: 8.2980. Min Act: -0.1700
Data Index: 5702925 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19