Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4855 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1951. Min Range: -5.1951
Max Act: 5.1951. Min Act: -0.1700
Data Index: 3332352 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.9451. Min Act: -0.1700
Data Index: 803489 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.8826. Min Act: -0.1700
Data Index: 5900045 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.9138. Min Act: -0.1700
Data Index: 3437692 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.8826. Min Act: -0.1700
Data Index: 274971 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.8826. Min Act: -0.1700
Data Index: 7949701 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.9138. Min Act: -0.1700
Data Index: 2465617 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.8513. Min Act: -0.1700
Data Index: 4851555 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.8201. Min Act: -0.1700
Data Index: 7685928 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.8201. Min Act: -0.1700
Data Index: 2891563 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.8201. Min Act: -0.1700
Data Index: 6874161 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.7888. Min Act: -0.1700
Data Index: 962782 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.7888. Min Act: -0.1700
Data Index: 7753167 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.7576. Min Act: -0.1700
Data Index: 5910998 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.7576. Min Act: -0.1700
Data Index: 5613535 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.7576. Min Act: -0.1700
Data Index: 1595487 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.7576. Min Act: -0.1700
Data Index: 7144981 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.7576. Min Act: -0.1700
Data Index: 1794175 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.7576. Min Act: -0.1700
Data Index: 6492395 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1951. Min Range: -5.1951
Max Act: 4.6951. Min Act: -0.1700
Data Index: 1167650 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19