Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.3921. Min Act: -0.1700
Data Index: 7387505 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.3608. Min Act: -0.1700
Data Index: 361243 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.2983. Min Act: -0.1700
Data Index: 1527394 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.2983. Min Act: -0.1700
Data Index: 7596838 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.3296. Min Act: -0.1700
Data Index: 7790951 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.2358. Min Act: -0.1700
Data Index: 4425762 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.2671. Min Act: -0.1700
Data Index: 5050783 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.2358. Min Act: -0.1700
Data Index: 3678783 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.2671. Min Act: -0.1700
Data Index: 2018007 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.2046. Min Act: -0.1700
Data Index: 4625303 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.2358. Min Act: -0.1700
Data Index: 6780854 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.1733. Min Act: -0.1700
Data Index: 4167140 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.1733. Min Act: -0.1700
Data Index: 1802804 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.1421. Min Act: -0.1700
Data Index: 4413630 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.1733. Min Act: -0.1700
Data Index: 6629212 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.1421. Min Act: -0.1700
Data Index: 2393453 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.1421. Min Act: -0.1700
Data Index: 5236253 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.1421. Min Act: -0.1700
Data Index: 5282997 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.1733. Min Act: -0.1700
Data Index: 7469994 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3921. Min Range: -5.3921
Max Act: 5.1108. Min Act: -0.1700
Data Index: 6094531 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19