Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2696 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1769. Min Range: -8.1769
Max Act: 8.1769. Min Act: -0.1700
Data Index: 8405475 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1769. Min Range: -8.1769
Max Act: 8.0206. Min Act: -0.1700
Data Index: 2138370 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.9894. Min Act: -0.1700
Data Index: 4602614 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.9894. Min Act: -0.1700
Data Index: 7283421 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.9581. Min Act: -0.1700
Data Index: 7736955 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.9269. Min Act: -0.1700
Data Index: 780928 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.9269. Min Act: -0.1700
Data Index: 3411764 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.8956. Min Act: -0.1699
Data Index: 526307 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.8644. Min Act: -0.1700
Data Index: 6941885 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.7706. Min Act: -0.1700
Data Index: 2093209 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.8019. Min Act: -0.1700
Data Index: 8672523 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.7394. Min Act: -0.1700
Data Index: 3501281 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.7706. Min Act: -0.1700
Data Index: 4079322 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.7706. Min Act: -0.1700
Data Index: 2909142 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.7706. Min Act: -0.1700
Data Index: 2438662 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.7394. Min Act: -0.1700
Data Index: 6373974 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.7081. Min Act: -0.1700
Data Index: 7531701 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.7081. Min Act: -0.1700
Data Index: 1952369 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.7081. Min Act: -0.1700
Data Index: 8585402 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1769. Min Range: -8.1769
Max Act: 7.6769. Min Act: -0.1700
Data Index: 8276028 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19