Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1268 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0030. Min Range: -9.0030
Max Act: 9.0030. Min Act: -0.1700
Data Index: 390607 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0030. Min Range: -9.0030
Max Act: 8.3155. Min Act: -0.1700
Data Index: 8036467 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0030. Min Range: -9.0030
Max Act: 8.0655. Min Act: -0.1700
Data Index: 1960850 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0030. Min Range: -9.0030
Max Act: 8.0655. Min Act: -0.1700
Data Index: 4183461 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0030. Min Range: -9.0030
Max Act: 8.0030. Min Act: -0.1700
Data Index: 226136 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.9405. Min Act: -0.1700
Data Index: 7127189 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.8780. Min Act: -0.1700
Data Index: 4170981 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.8780. Min Act: -0.1700
Data Index: 7186382 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.8780. Min Act: -0.1700
Data Index: 5834857 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.8155. Min Act: -0.1700
Data Index: 858965 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.8155. Min Act: -0.1700
Data Index: 1154329 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.8155. Min Act: -0.1700
Data Index: 1228539 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.8155. Min Act: -0.1700
Data Index: 3458853 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.7530. Min Act: -0.1700
Data Index: 680607 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.7530. Min Act: -0.1700
Data Index: 4309223 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.7530. Min Act: -0.1700
Data Index: 469935 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.6905. Min Act: -0.1700
Data Index: 8041420 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.6280. Min Act: -0.1700
Data Index: 1035390 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.5655. Min Act: -0.1700
Data Index: 2505374 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0030. Min Range: -9.0030
Max Act: 7.6280. Min Act: -0.1700
Data Index: 2670405 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19