Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3241 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.7589. Min Act: -0.1700
Data Index: 4367678 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.6964. Min Act: -0.1700
Data Index: 1623189 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.6964. Min Act: -0.1700
Data Index: 5942305 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.6339. Min Act: -0.1700
Data Index: 1617486 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.6339. Min Act: -0.1700
Data Index: 6197374 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.5402. Min Act: -0.1700
Data Index: 1219290 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.3214. Min Act: -0.1700
Data Index: 4489044 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.2589. Min Act: -0.1700
Data Index: 4847462 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.2277. Min Act: -0.1700
Data Index: 3185613 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.1964. Min Act: -0.1700
Data Index: 7195148 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.2277. Min Act: -0.1700
Data Index: 7794593 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.2277. Min Act: -0.1700
Data Index: 5268382 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.1964. Min Act: -0.1700
Data Index: 1464498 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.1339. Min Act: -0.1700
Data Index: 309726 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.1339. Min Act: -0.1700
Data Index: 4455688 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.1652. Min Act: -0.1700
Data Index: 602234 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.1027. Min Act: -0.1699
Data Index: 935187 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.1027. Min Act: -0.1700
Data Index: 5517202 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.1339. Min Act: -0.1700
Data Index: 5030110 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7589. Min Range: -7.7589
Max Act: 7.1027. Min Act: -0.1700
Data Index: 6487459 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19