Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4750 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.5685. Min Act: -0.1700
Data Index: 2531252 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.4748. Min Act: -0.1700
Data Index: 7953624 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.4122. Min Act: -0.1700
Data Index: 474190 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.4122. Min Act: -0.1700
Data Index: 5094444 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.4122. Min Act: -0.1700
Data Index: 918152 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.3810. Min Act: -0.1700
Data Index: 6378693 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.2872. Min Act: -0.1700
Data Index: 2897942 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.2560. Min Act: -0.1700
Data Index: 5309412 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.2560. Min Act: -0.1700
Data Index: 8172460 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.1935. Min Act: -0.1700
Data Index: 7110936 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.1935. Min Act: -0.1700
Data Index: 4327203 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.1935. Min Act: -0.1700
Data Index: 646055 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.1935. Min Act: -0.1700
Data Index: 1828614 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.2247. Min Act: -0.1700
Data Index: 5659556 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.1935. Min Act: -0.1700
Data Index: 5663095 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.1622. Min Act: -0.1700
Data Index: 7096913 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.1310. Min Act: -0.1700
Data Index: 2018108 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.1310. Min Act: -0.1700
Data Index: 7361755 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.1310. Min Act: -0.1700
Data Index: 7361803 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5685. Min Range: -4.5685
Max Act: 4.1622. Min Act: -0.1700
Data Index: 1679248 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19