Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 885 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0939. Min Range: -8.0939
Max Act: 8.0939. Min Act: -0.1700
Data Index: 3653027 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.7814. Min Act: -0.1700
Data Index: 2510206 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.6564. Min Act: -0.1700
Data Index: 416951 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.6564. Min Act: -0.1700
Data Index: 7109391 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.5939. Min Act: -0.1700
Data Index: 7323391 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.6564. Min Act: -0.1700
Data Index: 1132574 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.5939. Min Act: -0.1700
Data Index: 6791278 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.5939. Min Act: -0.1700
Data Index: 1910286 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.5939. Min Act: -0.1700
Data Index: 23400 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.5314. Min Act: -0.1700
Data Index: 2111550 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.5314. Min Act: -0.1700
Data Index: 888100 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.5314. Min Act: -0.1700
Data Index: 2233840 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.5314. Min Act: -0.1700
Data Index: 4662991 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.5314. Min Act: -0.1700
Data Index: 6655502 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.4377. Min Act: -0.1700
Data Index: 2970355 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.4377. Min Act: -0.1700
Data Index: 3614805 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.4064. Min Act: -0.1700
Data Index: 8623989 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.4377. Min Act: -0.1700
Data Index: 5490776 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.4064. Min Act: -0.1700
Data Index: 1574507 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0939. Min Range: -8.0939
Max Act: 7.4064. Min Act: -0.1700
Data Index: 1493762 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19