Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5711 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3576. Min Range: -11.3576
Max Act: 11.3576. Min Act: -0.1700
Data Index: 6366625 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3576. Min Range: -11.3576
Max Act: 11.2951. Min Act: -0.1700
Data Index: 6154725 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.7951. Min Act: -0.1700
Data Index: 5236676 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.6701. Min Act: -0.1700
Data Index: 4784328 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.6701. Min Act: -0.1700
Data Index: 1129764 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.6701. Min Act: -0.1700
Data Index: 2514040 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.6076. Min Act: -0.1700
Data Index: 5856980 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.5451. Min Act: -0.1700
Data Index: 1235845 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.5451. Min Act: -0.1700
Data Index: 5588049 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.5451. Min Act: -0.1700
Data Index: 2861866 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.4826. Min Act: -0.1700
Data Index: 4308062 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.5451. Min Act: -0.1700
Data Index: 6413533 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.3576. Min Act: -0.1700
Data Index: 6083928 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.2326. Min Act: -0.1700
Data Index: 8530130 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.2951. Min Act: -0.1700
Data Index: 7645645 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.2951. Min Act: -0.1700
Data Index: 2228161 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.2951. Min Act: -0.1700
Data Index: 567255 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.2326. Min Act: -0.1700
Data Index: 2418168 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.2951. Min Act: -0.1700
Data Index: 8426259 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3576. Min Range: -11.3576
Max Act: 10.1076. Min Act: -0.1700
Data Index: 1291006 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19