Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4344 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0194. Min Range: -7.0194
Max Act: 7.0194. Min Act: -0.1700
Data Index: 3630404 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0194. Min Range: -7.0194
Max Act: 7.0194. Min Act: -0.1700
Data Index: 499874 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.9881. Min Act: -0.1700
Data Index: 2637242 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.9569. Min Act: -0.1700
Data Index: 307184 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.9569. Min Act: -0.1700
Data Index: 6005288 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.9256. Min Act: -0.1700
Data Index: 5268214 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.8631. Min Act: -0.1700
Data Index: 5268215 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.8631. Min Act: -0.1700
Data Index: 6090948 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.8006. Min Act: -0.1700
Data Index: 2207220 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.8006. Min Act: -0.1700
Data Index: 8492146 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.7694. Min Act: -0.1700
Data Index: 8412803 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.7381. Min Act: -0.1700
Data Index: 5509620 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.7381. Min Act: -0.1700
Data Index: 4702162 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.7694. Min Act: -0.1700
Data Index: 375366 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.7381. Min Act: -0.1700
Data Index: 6086918 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.7069. Min Act: -0.1700
Data Index: 4668434 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.6756. Min Act: -0.1700
Data Index: 1652876 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.6444. Min Act: -0.1700
Data Index: 5169489 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.6444. Min Act: -0.1700
Data Index: 6124442 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0194. Min Range: -7.0194
Max Act: 6.6444. Min Act: -0.1700
Data Index: 4586292 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19