Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 875 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.8082. Min Act: -0.1700
Data Index: 8141713 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.7457. Min Act: -0.1700
Data Index: 448562 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.6832. Min Act: -0.1700
Data Index: 5403522 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.6832. Min Act: -0.1700
Data Index: 2265131 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.6832. Min Act: -0.1700
Data Index: 3824319 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.6832. Min Act: -0.1700
Data Index: 8043710 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.6832. Min Act: -0.1700
Data Index: 1172538 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.6519. Min Act: -0.1700
Data Index: 2959480 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.6519. Min Act: -0.1700
Data Index: 5886582 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.6207. Min Act: -0.1700
Data Index: 7652630 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.5894. Min Act: -0.1700
Data Index: 8251597 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.5582. Min Act: -0.1700
Data Index: 7982757 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.5269. Min Act: -0.1700
Data Index: 6520270 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.5269. Min Act: -0.1700
Data Index: 1620328 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.5269. Min Act: -0.1700
Data Index: 4698025 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.5269. Min Act: -0.1700
Data Index: 4473206 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.5269. Min Act: -0.1700
Data Index: 5358132 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.4957. Min Act: -0.1700
Data Index: 4902700 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.5269. Min Act: -0.1700
Data Index: 3924889 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8082. Min Range: -5.8082
Max Act: 5.4644. Min Act: -0.1700
Data Index: 171033 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19