Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1975 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0250. Min Range: -8.0250
Max Act: 8.0250. Min Act: -0.1700
Data Index: 629531 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.9937. Min Act: -0.1700
Data Index: 6938548 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.8687. Min Act: -0.1700
Data Index: 1458922 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.7750. Min Act: -0.1700
Data Index: 7031765 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.8062. Min Act: -0.1700
Data Index: 4233534 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.8062. Min Act: -0.1700
Data Index: 6425009 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.8062. Min Act: -0.1700
Data Index: 1765618 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.7125. Min Act: -0.1700
Data Index: 5857761 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.6812. Min Act: -0.1700
Data Index: 6248373 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.7125. Min Act: -0.1700
Data Index: 5175772 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.7125. Min Act: -0.1700
Data Index: 6239074 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.6500. Min Act: -0.1700
Data Index: 3207565 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.6187. Min Act: -0.1700
Data Index: 5076161 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.5875. Min Act: -0.1700
Data Index: 4919365 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.6187. Min Act: -0.1700
Data Index: 648872 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.6187. Min Act: -0.1700
Data Index: 6498335 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.5562. Min Act: -0.1700
Data Index: 7501997 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.5562. Min Act: -0.1700
Data Index: 5771996 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.5562. Min Act: -0.1700
Data Index: 3602429 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0250. Min Range: -8.0250
Max Act: 7.5562. Min Act: -0.1700
Data Index: 4498815 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19