Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4450 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0438. Min Range: -6.0438
Max Act: 6.0125. Min Act: -0.1700
Data Index: 3519120 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0438. Min Range: -6.0438
Max Act: 6.0438. Min Act: -0.1700
Data Index: 2844761 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.9813. Min Act: -0.1700
Data Index: 7153316 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.9813. Min Act: -0.1700
Data Index: 6074508 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.8875. Min Act: -0.1700
Data Index: 717257 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.8563. Min Act: -0.1700
Data Index: 2993156 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.8563. Min Act: -0.1700
Data Index: 6327748 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.8250. Min Act: -0.1700
Data Index: 6961994 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.7938. Min Act: -0.1700
Data Index: 2783777 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.7938. Min Act: -0.1700
Data Index: 5173503 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.7625. Min Act: -0.1700
Data Index: 8377792 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.7625. Min Act: -0.1700
Data Index: 725464 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.7625. Min Act: -0.1700
Data Index: 4104502 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.7000. Min Act: -0.1700
Data Index: 2815238 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.7000. Min Act: -0.1700
Data Index: 7803999 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.7313. Min Act: -0.1700
Data Index: 5191147 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.7625. Min Act: -0.1700
Data Index: 2775977 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.6688. Min Act: -0.1700
Data Index: 4995232 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.6688. Min Act: -0.1699
Data Index: 3519121 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0438. Min Range: -6.0438
Max Act: 5.6375. Min Act: -0.1700
Data Index: 5093044 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19