Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2627 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.3905. Min Act: -0.1700
Data Index: 4745035 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.3593. Min Act: -0.1700
Data Index: 8155400 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.2968. Min Act: -0.1700
Data Index: 3982603 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.2968. Min Act: -0.1700
Data Index: 7357431 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.2655. Min Act: -0.1700
Data Index: 7015757 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.2343. Min Act: -0.1700
Data Index: 4674636 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.2030. Min Act: -0.1700
Data Index: 3555011 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.2030. Min Act: -0.1700
Data Index: 3128836 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.1718. Min Act: -0.1700
Data Index: 8218021 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.2030. Min Act: -0.1700
Data Index: 786203 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.1405. Min Act: -0.1700
Data Index: 588175 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.1405. Min Act: -0.1700
Data Index: 7837468 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.1093. Min Act: -0.1700
Data Index: 1757303 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.1093. Min Act: -0.1700
Data Index: 442620 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.0780. Min Act: -0.1700
Data Index: 8065958 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.0780. Min Act: -0.1700
Data Index: 7357432 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.0780. Min Act: -0.1700
Data Index: 2653371 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.0780. Min Act: -0.1700
Data Index: 5438675 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.0468. Min Act: -0.1700
Data Index: 5740312 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3905. Min Range: -6.3905
Max Act: 6.0468. Min Act: -0.1700
Data Index: 491553 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19