Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1793 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.9560. Min Act: -0.1700
Data Index: 7731948 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.4560. Min Act: -0.1700
Data Index: 3032617 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.4248. Min Act: -0.1700
Data Index: 1449749 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.4248. Min Act: -0.1700
Data Index: 3700376 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.3935. Min Act: -0.1700
Data Index: 2787885 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.2998. Min Act: -0.1700
Data Index: 1508827 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.2060. Min Act: -0.1700
Data Index: 6575047 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.2060. Min Act: -0.1700
Data Index: 8733920 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.1748. Min Act: -0.1700
Data Index: 2536882 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.1435. Min Act: -0.1700
Data Index: 3386941 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.1748. Min Act: -0.1700
Data Index: 8274625 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.1123. Min Act: -0.1700
Data Index: 397453 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.1123. Min Act: -0.1700
Data Index: 3149854 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.0810. Min Act: -0.1700
Data Index: 35620 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.0498. Min Act: -0.1700
Data Index: 8229085 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.0185. Min Act: -0.1700
Data Index: 2212961 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9560. Min Range: -7.9560
Max Act: 7.0185. Min Act: -0.1700
Data Index: 3954045 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9560. Min Range: -7.9560
Max Act: 6.9873. Min Act: -0.1700
Data Index: 4717860 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9560. Min Range: -7.9560
Max Act: 6.9873. Min Act: -0.1700
Data Index: 3533183 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9560. Min Range: -7.9560
Max Act: 6.9248. Min Act: -0.1700
Data Index: 605986 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19