Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 604 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.9909. Min Act: -0.1700
Data Index: 7430758 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.8659. Min Act: -0.1700
Data Index: 5663050 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.6784. Min Act: -0.1700
Data Index: 5711024 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.7409. Min Act: -0.1700
Data Index: 165751 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.6784. Min Act: -0.1700
Data Index: 1901454 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.6784. Min Act: -0.1700
Data Index: 7054406 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.6784. Min Act: -0.1700
Data Index: 4031515 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.6784. Min Act: -0.1700
Data Index: 2664859 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.6159. Min Act: -0.1700
Data Index: 5543629 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.6159. Min Act: -0.1700
Data Index: 2520790 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.6159. Min Act: -0.1700
Data Index: 2944416 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.6159. Min Act: -0.1700
Data Index: 6815237 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.6784. Min Act: -0.1700
Data Index: 6202102 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.5534. Min Act: -0.1700
Data Index: 420029 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.5534. Min Act: -0.1700
Data Index: 2608452 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.5534. Min Act: -0.1700
Data Index: 3456098 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.4909. Min Act: -0.1700
Data Index: 7168042 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.5534. Min Act: -0.1700
Data Index: 3388305 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.4909. Min Act: -0.1700
Data Index: 2586458 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9909. Min Range: -8.9909
Max Act: 8.5534. Min Act: -0.1700
Data Index: 5458510 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19