Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1247 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.7272. Min Act: -0.1700
Data Index: 8386873 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.2272. Min Act: -0.1700
Data Index: 7658010 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.1647. Min Act: -0.1700
Data Index: 511525 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.1335. Min Act: -0.1700
Data Index: 4024987 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.1335. Min Act: -0.1700
Data Index: 4575903 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.1022. Min Act: -0.1700
Data Index: 4257609 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.0085. Min Act: -0.1700
Data Index: 8626952 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.0085. Min Act: -0.1700
Data Index: 3325615 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7272. Min Range: -6.7272
Max Act: 5.9147. Min Act: -0.1700
Data Index: 6868044 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7272. Min Range: -6.7272
Max Act: 5.8835. Min Act: -0.1700
Data Index: 6083204 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7272. Min Range: -6.7272
Max Act: 5.9147. Min Act: -0.1700
Data Index: 6511898 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7272. Min Range: -6.7272
Max Act: 5.9147. Min Act: -0.1700
Data Index: 2188076 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7272. Min Range: -6.7272
Max Act: 5.8835. Min Act: -0.1700
Data Index: 633601 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7272. Min Range: -6.7272
Max Act: 5.8522. Min Act: -0.1700
Data Index: 2957898 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7272. Min Range: -6.7272
Max Act: 5.8522. Min Act: -0.1700
Data Index: 334916 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7272. Min Range: -6.7272
Max Act: 5.8210. Min Act: -0.1700
Data Index: 3521988 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7272. Min Range: -6.7272
Max Act: 5.7897. Min Act: -0.1700
Data Index: 330453 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7272. Min Range: -6.7272
Max Act: 5.7897. Min Act: -0.1700
Data Index: 3990593 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7272. Min Range: -6.7272
Max Act: 5.7897. Min Act: -0.1700
Data Index: 3273085 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7272. Min Range: -6.7272
Max Act: 5.7585. Min Act: -0.1700
Data Index: 1893040 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19