Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6059 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.8099. Min Act: -0.1700
Data Index: 4841942 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.7161. Min Act: -0.1700
Data Index: 1333060 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4661. Min Act: -0.1700
Data Index: 3280099 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4974. Min Act: -0.1700
Data Index: 1483814 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4974. Min Act: -0.1700
Data Index: 6028560 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4974. Min Act: -0.1700
Data Index: 5339375 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4349. Min Act: -0.1700
Data Index: 4985594 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4661. Min Act: -0.1700
Data Index: 7069786 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 6496088 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 6484319 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 4934839 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3411. Min Act: -0.1700
Data Index: 7684841 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.2786. Min Act: -0.1700
Data Index: 3110977 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.2786. Min Act: -0.1700
Data Index: 6801024 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.2474. Min Act: -0.1700
Data Index: 3280096 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.2786. Min Act: -0.1700
Data Index: 6994643 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.2474. Min Act: -0.1700
Data Index: 518098 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.2161. Min Act: -0.1700
Data Index: 3280097 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.1849. Min Act: -0.1700
Data Index: 6963359 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.1849. Min Act: -0.1700
Data Index: 2343134 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19