Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 333 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5880. Min Range: -5.5880
Max Act: 5.5880. Min Act: -0.1700
Data Index: 2852830 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5880. Min Range: -5.5880
Max Act: 5.2130. Min Act: -0.1700
Data Index: 422665 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5880. Min Range: -5.5880
Max Act: 5.2130. Min Act: -0.1700
Data Index: 4242740 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5880. Min Range: -5.5880
Max Act: 5.1505. Min Act: -0.1700
Data Index: 8445111 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5880. Min Range: -5.5880
Max Act: 5.0568. Min Act: -0.1700
Data Index: 3554141 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.9943. Min Act: -0.1700
Data Index: 6357587 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.9630. Min Act: -0.1700
Data Index: 8307042 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.9630. Min Act: -0.1700
Data Index: 368413 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.9318. Min Act: -0.1700
Data Index: 2644365 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.9005. Min Act: -0.1700
Data Index: 157509 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.8693. Min Act: -0.1700
Data Index: 4803260 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.8693. Min Act: -0.1700
Data Index: 8286023 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.9005. Min Act: -0.1700
Data Index: 2061409 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.8693. Min Act: -0.1700
Data Index: 3270226 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.8068. Min Act: -0.1700
Data Index: 115154 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.8068. Min Act: -0.1700
Data Index: 102586 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.7755. Min Act: -0.1700
Data Index: 1207290 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.7755. Min Act: -0.1700
Data Index: 1255837 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.7443. Min Act: -0.1700
Data Index: 1050981 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5880. Min Range: -5.5880
Max Act: 4.7755. Min Act: -0.1700
Data Index: 7359200 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19