Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6380 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0381. Min Range: -8.0381
Max Act: 8.0381. Min Act: -0.1700
Data Index: 365856 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.6006. Min Act: -0.1700
Data Index: 1734986 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.5068. Min Act: -0.1700
Data Index: 1734990 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.3193. Min Act: -0.1700
Data Index: 6051716 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.2568. Min Act: -0.1700
Data Index: 1943582 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.2568. Min Act: -0.1700
Data Index: 5152647 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.2256. Min Act: -0.1700
Data Index: 1081437 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.1943. Min Act: -0.1700
Data Index: 5259898 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.1631. Min Act: -0.1700
Data Index: 7732253 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.1318. Min Act: -0.1700
Data Index: 637308 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.1006. Min Act: -0.1700
Data Index: 5848042 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.0381. Min Act: -0.1700
Data Index: 209019 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.0068. Min Act: -0.1700
Data Index: 3753084 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.0068. Min Act: -0.1700
Data Index: 5780253 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0381. Min Range: -8.0381
Max Act: 7.0068. Min Act: -0.1700
Data Index: 3868138 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0381. Min Range: -8.0381
Max Act: 6.9756. Min Act: -0.1700
Data Index: 1259331 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0381. Min Range: -8.0381
Max Act: 6.9756. Min Act: -0.1700
Data Index: 3850190 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0381. Min Range: -8.0381
Max Act: 6.9756. Min Act: -0.1700
Data Index: 2251677 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0381. Min Range: -8.0381
Max Act: 6.9756. Min Act: -0.1700
Data Index: 4056455 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0381. Min Range: -8.0381
Max Act: 6.9443. Min Act: -0.1700
Data Index: 3016834 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19