Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3741 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6246. Min Range: -7.6246
Max Act: 7.6246. Min Act: -0.1700
Data Index: 6050471 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6246. Min Range: -7.6246
Max Act: 7.2496. Min Act: -0.1700
Data Index: 423565 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6246. Min Range: -7.6246
Max Act: 7.2496. Min Act: -0.1700
Data Index: 800215 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6246. Min Range: -7.6246
Max Act: 7.2184. Min Act: -0.1700
Data Index: 1472057 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6246. Min Range: -7.6246
Max Act: 7.0934. Min Act: -0.1700
Data Index: 1832278 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6246. Min Range: -7.6246
Max Act: 7.0309. Min Act: -0.1700
Data Index: 8329286 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6246. Min Range: -7.6246
Max Act: 7.0309. Min Act: -0.1700
Data Index: 6729920 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6246. Min Range: -7.6246
Max Act: 6.9996. Min Act: -0.1700
Data Index: 5342964 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6246. Min Range: -7.6246
Max Act: 6.9684. Min Act: -0.1700
Data Index: 1447597 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6246. Min Range: -7.6246
Max Act: 6.9059. Min Act: -0.1700
Data Index: 6974403 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6246. Min Range: -7.6246
Max Act: 6.9059. Min Act: -0.1700
Data Index: 2280431 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6246. Min Range: -7.6246
Max Act: 6.8746. Min Act: -0.1700
Data Index: 7808403 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6246. Min Range: -7.6246
Max Act: 6.8746. Min Act: -0.1700
Data Index: 6317700 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6246. Min Range: -7.6246
Max Act: 6.8121. Min Act: -0.1700
Data Index: 1583045 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6246. Min Range: -7.6246
Max Act: 6.8746. Min Act: -0.1700
Data Index: 4771324 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6246. Min Range: -7.6246
Max Act: 6.8434. Min Act: -0.1700
Data Index: 1598992 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6246. Min Range: -7.6246
Max Act: 6.8121. Min Act: -0.1700
Data Index: 1850629 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6246. Min Range: -7.6246
Max Act: 6.8121. Min Act: -0.1700
Data Index: 6738749 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6246. Min Range: -7.6246
Max Act: 6.8121. Min Act: -0.1700
Data Index: 4382983 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6246. Min Range: -7.6246
Max Act: 6.7809. Min Act: -0.1700
Data Index: 3057316 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19