Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.5596. Min Act: -0.1700
Data Index: 3288476 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.5596. Min Act: -0.1700
Data Index: 2046802 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.4346. Min Act: -0.1700
Data Index: 775638 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.4346. Min Act: -0.1700
Data Index: 1004651 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.4034. Min Act: -0.1700
Data Index: 3593462 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.3409. Min Act: -0.1700
Data Index: 2119236 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.2784. Min Act: -0.1700
Data Index: 1730389 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.3096. Min Act: -0.1700
Data Index: 5027843 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.2471. Min Act: -0.1700
Data Index: 4270759 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.2784. Min Act: -0.1700
Data Index: 8805744 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.2471. Min Act: -0.1700
Data Index: 5788718 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.2159. Min Act: -0.1700
Data Index: 7958528 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.2784. Min Act: -0.1700
Data Index: 6393926 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.1846. Min Act: -0.1700
Data Index: 2670697 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.2159. Min Act: -0.1700
Data Index: 2119229 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.2471. Min Act: -0.1700
Data Index: 3177466 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.2471. Min Act: -0.1700
Data Index: 819016 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.2159. Min Act: -0.1700
Data Index: 4125158 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.1846. Min Act: -0.1700
Data Index: 4841019 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5596. Min Range: -7.5596
Max Act: 7.1846. Min Act: -0.1700
Data Index: 6058399 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19