Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4278 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1151. Min Range: -5.1151
Max Act: 5.1151. Min Act: -0.1700
Data Index: 4151703 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1151. Min Range: -5.1151
Max Act: 5.0838. Min Act: -0.1700
Data Index: 7568355 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1151. Min Range: -5.1151
Max Act: 5.0213. Min Act: -0.1700
Data Index: 7568352 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1151. Min Range: -5.1151
Max Act: 5.0213. Min Act: -0.1700
Data Index: 6021911 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.9276. Min Act: -0.1700
Data Index: 3064066 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.9588. Min Act: -0.1700
Data Index: 4064735 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.9276. Min Act: -0.1700
Data Index: 3779059 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.9276. Min Act: -0.1700
Data Index: 1379505 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.8963. Min Act: -0.1700
Data Index: 5612776 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.9276. Min Act: -0.1700
Data Index: 6900881 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.9276. Min Act: -0.1700
Data Index: 8407950 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.8963. Min Act: -0.1700
Data Index: 6420109 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.8963. Min Act: -0.1700
Data Index: 7721080 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.8963. Min Act: -0.1700
Data Index: 4295979 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.8338. Min Act: -0.1700
Data Index: 6138560 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.8651. Min Act: -0.1700
Data Index: 4037190 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.8651. Min Act: -0.1700
Data Index: 6844396 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.8338. Min Act: -0.1700
Data Index: 5411220 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.8338. Min Act: -0.1700
Data Index: 50291 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1151. Min Range: -5.1151
Max Act: 4.8651. Min Act: -0.1700
Data Index: 5302719 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19