Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5419 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3680. Min Range: -8.3680
Max Act: 8.3680. Min Act: -0.1700
Data Index: 1163461 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3680. Min Range: -8.3680
Max Act: 8.1805. Min Act: -0.1700
Data Index: 5984019 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3680. Min Range: -8.3680
Max Act: 8.1180. Min Act: -0.1700
Data Index: 1104044 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3680. Min Range: -8.3680
Max Act: 8.0555. Min Act: -0.1700
Data Index: 8495335 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.9305. Min Act: -0.1700
Data Index: 7913118 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.9305. Min Act: -0.1700
Data Index: 5520654 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.8680. Min Act: -0.1700
Data Index: 959671 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.8680. Min Act: -0.1700
Data Index: 1055943 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.8680. Min Act: -0.1700
Data Index: 2179962 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.8055. Min Act: -0.1700
Data Index: 2784644 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.7430. Min Act: -0.1700
Data Index: 1478594 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.7430. Min Act: -0.1700
Data Index: 336778 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.6805. Min Act: -0.1700
Data Index: 6778315 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.7430. Min Act: -0.1700
Data Index: 5392707 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.7430. Min Act: -0.1700
Data Index: 5503854 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.7430. Min Act: -0.1700
Data Index: 4088810 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.7430. Min Act: -0.1700
Data Index: 5312867 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.7430. Min Act: -0.1700
Data Index: 8704049 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.6805. Min Act: -0.1700
Data Index: 7283345 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3680. Min Range: -8.3680
Max Act: 7.6805. Min Act: -0.1700
Data Index: 7660533 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19