Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5580 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.3273. Min Act: -0.1700
Data Index: 3277903 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.2959. Min Act: -0.1700
Data Index: 8297273 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.2959. Min Act: -0.1700
Data Index: 2893210 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.2645. Min Act: -0.1700
Data Index: 6535649 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.2645. Min Act: -0.1700
Data Index: 4508055 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.2645. Min Act: -0.1700
Data Index: 1495878 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.2645. Min Act: -0.1700
Data Index: 4011984 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.2645. Min Act: -0.1700
Data Index: 8601852 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.2331. Min Act: -0.1700
Data Index: 2020370 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.2331. Min Act: -0.1700
Data Index: 5542866 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.2016. Min Act: -0.1700
Data Index: 5823104 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.2016. Min Act: -0.1700
Data Index: 8601853 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.2016. Min Act: -0.1700
Data Index: 4763622 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.2016. Min Act: -0.1700
Data Index: 2245078 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.1702. Min Act: -0.1700
Data Index: 1881807 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.1702. Min Act: -0.1700
Data Index: 2462426 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.1387. Min Act: -0.1700
Data Index: 8256638 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.1387. Min Act: -0.1700
Data Index: 6571755 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.1387. Min Act: -0.1700
Data Index: 4813123 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3273. Min Range: -3.3273
Max Act: 3.1387. Min Act: -0.1700
Data Index: 4896316 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19