Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1305 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.8885. Min Act: -0.1700
Data Index: 1644781 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.8572. Min Act: -0.1700
Data Index: 6535462 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.7635. Min Act: -0.1700
Data Index: 7457727 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.7010. Min Act: -0.1700
Data Index: 5630953 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.7322. Min Act: -0.1700
Data Index: 4127785 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.6697. Min Act: -0.1700
Data Index: 1370498 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.6697. Min Act: -0.1700
Data Index: 7644103 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.6697. Min Act: -0.1700
Data Index: 7901677 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.6385. Min Act: -0.1700
Data Index: 5208846 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.6385. Min Act: -0.1700
Data Index: 4484982 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.6072. Min Act: -0.1700
Data Index: 8436114 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.5760. Min Act: -0.1700
Data Index: 5201085 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.6072. Min Act: -0.1700
Data Index: 6231258 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.6072. Min Act: -0.1700
Data Index: 6960124 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.6072. Min Act: -0.1700
Data Index: 1403435 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.6072. Min Act: -0.1700
Data Index: 3714856 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.5760. Min Act: -0.1700
Data Index: 4166514 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.6072. Min Act: -0.1700
Data Index: 6136021 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.5760. Min Act: -0.1700
Data Index: 1003108 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8885. Min Range: -4.8885
Max Act: 4.5760. Min Act: -0.1700
Data Index: 2496537 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19