Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3434 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3145. Min Range: -9.3145
Max Act: 9.3145. Min Act: -0.1700
Data Index: 6908563 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3145. Min Range: -9.3145
Max Act: 9.0645. Min Act: -0.1700
Data Index: 3706508 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.9395. Min Act: -0.1700
Data Index: 919608 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.8770. Min Act: -0.1700
Data Index: 3938394 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.8770. Min Act: -0.1700
Data Index: 7116984 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.8145. Min Act: -0.1700
Data Index: 6380837 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.6895. Min Act: -0.1700
Data Index: 8742879 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.6270. Min Act: -0.1700
Data Index: 5656954 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.5645. Min Act: -0.1700
Data Index: 4910083 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.5020. Min Act: -0.1700
Data Index: 6007971 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.5020. Min Act: -0.1700
Data Index: 747187 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.4395. Min Act: -0.1700
Data Index: 4610513 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.5020. Min Act: -0.1700
Data Index: 4029067 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.5020. Min Act: -0.1700
Data Index: 8764747 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.4395. Min Act: -0.1700
Data Index: 1397218 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.4395. Min Act: -0.1700
Data Index: 2630245 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.4395. Min Act: -0.1700
Data Index: 4214996 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.4395. Min Act: -0.1700
Data Index: 7914380 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.4395. Min Act: -0.1700
Data Index: 8320588 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3145. Min Range: -9.3145
Max Act: 8.4395. Min Act: -0.1700
Data Index: 5863630 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19