Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.9919. Min Act: -0.1700
Data Index: 7630339 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.7574. Min Act: -0.1700
Data Index: 387862 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.6948. Min Act: -0.1700
Data Index: 5466562 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.7261. Min Act: -0.1700
Data Index: 4181656 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.6948. Min Act: -0.1700
Data Index: 8406285 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.6322. Min Act: -0.1700
Data Index: 389480 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.6322. Min Act: -0.1700
Data Index: 1642832 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.5853. Min Act: -0.1700
Data Index: 1246524 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.5696. Min Act: -0.1700
Data Index: 2600376 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.5853. Min Act: -0.1700
Data Index: 2298993 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.5540. Min Act: -0.1700
Data Index: 7878476 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.5540. Min Act: -0.1700
Data Index: 8372972 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.5226. Min Act: -0.1700
Data Index: 466816 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.5226. Min Act: -0.1700
Data Index: 2560133 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.5226. Min Act: -0.1700
Data Index: 1424972 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.5070. Min Act: -0.1700
Data Index: 6586684 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.5070. Min Act: -0.1700
Data Index: 7471259 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.4913. Min Act: -0.1700
Data Index: 4149516 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.4913. Min Act: -0.1700
Data Index: 5048498 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9919. Min Range: -3.9919
Max Act: 3.4757. Min Act: -0.1700
Data Index: 7614214 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19