Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5238 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2787. Min Range: -8.2787
Max Act: 8.2787. Min Act: -0.1700
Data Index: 5884997 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2787. Min Range: -8.2787
Max Act: 8.2787. Min Act: -0.1700
Data Index: 7324448 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2787. Min Range: -8.2787
Max Act: 8.1537. Min Act: -0.1700
Data Index: 2822395 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.9350. Min Act: -0.1700
Data Index: 4300216 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.9037. Min Act: -0.1700
Data Index: 4300217 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.7787. Min Act: -0.1700
Data Index: 6055981 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.7787. Min Act: -0.1700
Data Index: 6055990 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.7475. Min Act: -0.1700
Data Index: 6055984 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.7475. Min Act: -0.1700
Data Index: 2910863 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.6850. Min Act: -0.1700
Data Index: 5884998 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.6537. Min Act: -0.1700
Data Index: 5885003 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.6537. Min Act: -0.1700
Data Index: 5723376 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.6225. Min Act: -0.1700
Data Index: 6413621 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.6225. Min Act: -0.1700
Data Index: 6055996 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.5600. Min Act: -0.1700
Data Index: 5884999 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.5287. Min Act: -0.1700
Data Index: 6055989 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.4662. Min Act: -0.1700
Data Index: 6055976 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.4975. Min Act: -0.1700
Data Index: 6055993 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.4662. Min Act: -0.1700
Data Index: 6055967 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2787. Min Range: -8.2787
Max Act: 7.4037. Min Act: -0.1700
Data Index: 6055995 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19