Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4702 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.9985. Min Act: -0.1700
Data Index: 5815 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.7485. Min Act: -0.1700
Data Index: 713553 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.5610. Min Act: -0.1700
Data Index: 2069845 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.5610. Min Act: -0.1700
Data Index: 8497135 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.4985. Min Act: -0.1700
Data Index: 6274880 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.3735. Min Act: -0.1700
Data Index: 957148 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.3735. Min Act: -0.1700
Data Index: 4379325 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.3110. Min Act: -0.1700
Data Index: 5930402 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.1860. Min Act: -0.1700
Data Index: 3928489 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.2485. Min Act: -0.1700
Data Index: 3889286 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.2485. Min Act: -0.1700
Data Index: 5234403 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.1860. Min Act: -0.1700
Data Index: 3655192 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.1860. Min Act: -0.1700
Data Index: 2545443 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.1235. Min Act: -0.1700
Data Index: 3224471 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.1860. Min Act: -0.1700
Data Index: 4118000 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.1860. Min Act: -0.1700
Data Index: 153877 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.1860. Min Act: -0.1700
Data Index: 612098 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.1235. Min Act: -0.1700
Data Index: 428043 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.1235. Min Act: -0.1700
Data Index: 3024885 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9985. Min Range: -9.9985
Max Act: 9.1235. Min Act: -0.1700
Data Index: 4381510 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19