Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4897 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.3924. Min Act: -0.1700
Data Index: 4753294 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.2049. Min Act: -0.1700
Data Index: 6974653 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.1424. Min Act: -0.1700
Data Index: 787831 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.1111. Min Act: -0.1700
Data Index: 519124 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.1111. Min Act: -0.1700
Data Index: 8677355 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.0799. Min Act: -0.1700
Data Index: 8496457 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.0486. Min Act: -0.1700
Data Index: 8768339 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.0174. Min Act: -0.1700
Data Index: 8570786 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.0486. Min Act: -0.1700
Data Index: 2325222 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.0174. Min Act: -0.1700
Data Index: 7520183 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.0486. Min Act: -0.1700
Data Index: 850279 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.0486. Min Act: -0.1700
Data Index: 7240004 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3924. Min Range: -5.3924
Max Act: 5.0174. Min Act: -0.1700
Data Index: 2927435 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.9861. Min Act: -0.1700
Data Index: 566340 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.9549. Min Act: -0.1700
Data Index: 1079522 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.9236. Min Act: -0.1700
Data Index: 5667203 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.9236. Min Act: -0.1700
Data Index: 832581 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.9236. Min Act: -0.1700
Data Index: 7285110 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.8924. Min Act: -0.1700
Data Index: 7508839 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3924. Min Range: -5.3924
Max Act: 4.9236. Min Act: -0.1700
Data Index: 3715485 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19