Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1620 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7458. Min Range: -9.7458
Max Act: 9.7458. Min Act: -0.1700
Data Index: 4671711 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.7458. Min Act: -0.1700
Data Index: 5775842 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.6833. Min Act: -0.1700
Data Index: 1008810 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.6833. Min Act: -0.1700
Data Index: 6462605 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.6208. Min Act: -0.1700
Data Index: 2455548 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.6833. Min Act: -0.1700
Data Index: 2032639 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.6208. Min Act: -0.1700
Data Index: 6091503 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.6208. Min Act: -0.1700
Data Index: 6657695 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.5583. Min Act: -0.1700
Data Index: 4500528 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.4958. Min Act: -0.1700
Data Index: 4844940 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.5583. Min Act: -0.1700
Data Index: 2464768 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.4958. Min Act: -0.1700
Data Index: 6962799 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.4958. Min Act: -0.1700
Data Index: 3120508 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.4958. Min Act: -0.1700
Data Index: 5699692 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.4958. Min Act: -0.1700
Data Index: 4247532 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.4958. Min Act: -0.1700
Data Index: 1205701 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.4333. Min Act: -0.1700
Data Index: 4812560 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.4333. Min Act: -0.1700
Data Index: 3203513 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.4333. Min Act: -0.1700
Data Index: 996782 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7458. Min Range: -9.7458
Max Act: 8.3708. Min Act: -0.1700
Data Index: 2641380 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19