Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1605 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.9438. Min Act: -0.1700
Data Index: 3443733 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.6625. Min Act: -0.1700
Data Index: 1972433 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.4125. Min Act: -0.1700
Data Index: 979453 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.3500. Min Act: -0.1700
Data Index: 4248437 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.3188. Min Act: -0.1700
Data Index: 1010513 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.2875. Min Act: -0.1700
Data Index: 5122236 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.2563. Min Act: -0.1700
Data Index: 3088702 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.2563. Min Act: -0.1700
Data Index: 1803926 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.2563. Min Act: -0.1700
Data Index: 3088990 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.1938. Min Act: -0.1700
Data Index: 6782282 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.1000. Min Act: -0.1700
Data Index: 8295172 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.1313. Min Act: -0.1700
Data Index: 5538282 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.1000. Min Act: -0.1700
Data Index: 625633 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.1000. Min Act: -0.1700
Data Index: 3150877 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.0688. Min Act: -0.1700
Data Index: 435554 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.0688. Min Act: -0.1700
Data Index: 5739122 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.0688. Min Act: -0.1700
Data Index: 7118260 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.0688. Min Act: -0.1700
Data Index: 624641 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.0688. Min Act: -0.1700
Data Index: 3693826 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9438. Min Range: -6.9438
Max Act: 6.0688. Min Act: -0.1700
Data Index: 7406747 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19