Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3238 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1981. Min Range: -8.1981
Max Act: 8.1981. Min Act: -0.1700
Data Index: 8465572 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1981. Min Range: -8.1981
Max Act: 8.1356. Min Act: -0.1700
Data Index: 4605504 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.5731. Min Act: -0.1700
Data Index: 1423555 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.4794. Min Act: -0.1700
Data Index: 7900982 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.4481. Min Act: -0.1700
Data Index: 4839694 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.4169. Min Act: -0.1700
Data Index: 4390498 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.3856. Min Act: -0.1700
Data Index: 2822017 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.3856. Min Act: -0.1700
Data Index: 7744722 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.2606. Min Act: -0.1700
Data Index: 8279396 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.2919. Min Act: -0.1700
Data Index: 782166 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.2294. Min Act: -0.1700
Data Index: 3193187 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.1981. Min Act: -0.1700
Data Index: 3776884 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.1356. Min Act: -0.1700
Data Index: 463616 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.0731. Min Act: -0.1700
Data Index: 223720 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.0731. Min Act: -0.1700
Data Index: 689377 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.0106. Min Act: -0.1700
Data Index: 3984108 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1981. Min Range: -8.1981
Max Act: 7.0419. Min Act: -0.1700
Data Index: 6355015 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1981. Min Range: -8.1981
Max Act: 6.9794. Min Act: -0.1700
Data Index: 8297607 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1981. Min Range: -8.1981
Max Act: 6.9481. Min Act: -0.1700
Data Index: 7396180 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1981. Min Range: -8.1981
Max Act: 6.9481. Min Act: -0.1700
Data Index: 7757420 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19