Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1729 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1845. Min Range: -8.1845
Max Act: 8.1845. Min Act: -0.1700
Data Index: 3755397 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.8095. Min Act: -0.1700
Data Index: 478726 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.7783. Min Act: -0.1700
Data Index: 7703047 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.8095. Min Act: -0.1700
Data Index: 6433626 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.7470. Min Act: -0.1700
Data Index: 6152534 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.6845. Min Act: -0.1700
Data Index: 4889967 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.6845. Min Act: -0.1700
Data Index: 940104 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.6845. Min Act: -0.1700
Data Index: 2864176 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.6220. Min Act: -0.1700
Data Index: 2128345 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.6220. Min Act: -0.1700
Data Index: 8636028 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.5908. Min Act: -0.1700
Data Index: 561887 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.5908. Min Act: -0.1700
Data Index: 8033840 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.5595. Min Act: -0.1700
Data Index: 3134654 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.5283. Min Act: -0.1700
Data Index: 2351944 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.5283. Min Act: -0.1700
Data Index: 1363069 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.5595. Min Act: -0.1700
Data Index: 2455244 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.5283. Min Act: -0.1700
Data Index: 2738669 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.4970. Min Act: -0.1700
Data Index: 2280716 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.4970. Min Act: -0.1700
Data Index: 8376773 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1845. Min Range: -8.1845
Max Act: 7.4658. Min Act: -0.1700
Data Index: 7086905 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19