Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1268. Min Range: -6.1268
Max Act: 6.1268. Min Act: -0.1700
Data Index: 1335269 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1268. Min Range: -6.1268
Max Act: 6.1268. Min Act: -0.1700
Data Index: 4627461 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1268. Min Range: -6.1268
Max Act: 6.1268. Min Act: -0.1700
Data Index: 2274694 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1268. Min Range: -6.1268
Max Act: 6.0956. Min Act: -0.1700
Data Index: 7277521 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1268. Min Range: -6.1268
Max Act: 6.0956. Min Act: -0.1700
Data Index: 5221328 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1268. Min Range: -6.1268
Max Act: 6.0643. Min Act: -0.1700
Data Index: 4645694 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1268. Min Range: -6.1268
Max Act: 6.0331. Min Act: -0.1700
Data Index: 5979794 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1268. Min Range: -6.1268
Max Act: 5.9706. Min Act: -0.1700
Data Index: 6661802 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1268. Min Range: -6.1268
Max Act: 5.9393. Min Act: -0.1700
Data Index: 8641292 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1268. Min Range: -6.1268
Max Act: 5.9081. Min Act: -0.1700
Data Index: 1003798 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1268. Min Range: -6.1268
Max Act: 5.8768. Min Act: -0.1700
Data Index: 8452989 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1268. Min Range: -6.1268
Max Act: 5.8768. Min Act: -0.1700
Data Index: 4712759 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1268. Min Range: -6.1268
Max Act: 5.8768. Min Act: -0.1700
Data Index: 8382906 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1268. Min Range: -6.1268
Max Act: 5.8456. Min Act: -0.1700
Data Index: 1963890 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1268. Min Range: -6.1268
Max Act: 5.8768. Min Act: -0.1700
Data Index: 8400297 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1268. Min Range: -6.1268
Max Act: 5.8456. Min Act: -0.1700
Data Index: 4254250 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1268. Min Range: -6.1268
Max Act: 5.7831. Min Act: -0.1700
Data Index: 4585111 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1268. Min Range: -6.1268
Max Act: 5.8143. Min Act: -0.1700
Data Index: 2394876 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1268. Min Range: -6.1268
Max Act: 5.8143. Min Act: -0.1700
Data Index: 1553832 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1268. Min Range: -6.1268
Max Act: 5.8143. Min Act: -0.1700
Data Index: 119635 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19