Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3442. Min Range: -6.3442
Max Act: 6.3442. Min Act: -0.1700
Data Index: 6432816 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3442. Min Range: -6.3442
Max Act: 6.3129. Min Act: -0.1700
Data Index: 1601088 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3442. Min Range: -6.3442
Max Act: 6.3129. Min Act: -0.1700
Data Index: 8515314 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3442. Min Range: -6.3442
Max Act: 6.1567. Min Act: -0.1700
Data Index: 2500601 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3442. Min Range: -6.3442
Max Act: 6.0942. Min Act: -0.1700
Data Index: 475616 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3442. Min Range: -6.3442
Max Act: 6.0942. Min Act: -0.1700
Data Index: 2418453 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3442. Min Range: -6.3442
Max Act: 6.0629. Min Act: -0.1700
Data Index: 4816271 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3442. Min Range: -6.3442
Max Act: 6.0317. Min Act: -0.1700
Data Index: 8526740 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3442. Min Range: -6.3442
Max Act: 6.0004. Min Act: -0.1700
Data Index: 770511 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.9692. Min Act: -0.1700
Data Index: 1219002 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.9692. Min Act: -0.1700
Data Index: 4793621 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.9379. Min Act: -0.1700
Data Index: 7658463 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.8754. Min Act: -0.1700
Data Index: 5804589 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.8754. Min Act: -0.1700
Data Index: 4894118 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.8754. Min Act: -0.1700
Data Index: 6936558 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.8129. Min Act: -0.1700
Data Index: 8178986 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.8129. Min Act: -0.1700
Data Index: 3103810 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.8129. Min Act: -0.1700
Data Index: 4051610 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.8129. Min Act: -0.1700
Data Index: 6218985 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3442. Min Range: -6.3442
Max Act: 5.8129. Min Act: -0.1700
Data Index: 5119085 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19