Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3996 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0369. Min Range: -7.0369
Max Act: 7.0369. Min Act: -0.1700
Data Index: 7765498 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0369. Min Range: -7.0369
Max Act: 7.0057. Min Act: -0.1700
Data Index: 3233120 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0369. Min Range: -7.0369
Max Act: 7.0057. Min Act: -0.1700
Data Index: 7789473 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.9744. Min Act: -0.1700
Data Index: 2558810 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.8182. Min Act: -0.1700
Data Index: 7791778 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.7869. Min Act: -0.1700
Data Index: 1429062 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.7869. Min Act: -0.1700
Data Index: 1646807 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.7557. Min Act: -0.1700
Data Index: 698199 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.7244. Min Act: -0.1700
Data Index: 5716465 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.7244. Min Act: -0.1700
Data Index: 4258652 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.7244. Min Act: -0.1700
Data Index: 3571464 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.6932. Min Act: -0.1700
Data Index: 4448113 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.6932. Min Act: -0.1700
Data Index: 7664727 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.6307. Min Act: -0.1700
Data Index: 7796041 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.6307. Min Act: -0.1700
Data Index: 7110371 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.6307. Min Act: -0.1700
Data Index: 4232742 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.5682. Min Act: -0.1700
Data Index: 2793341 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.5994. Min Act: -0.1700
Data Index: 3579140 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.5682. Min Act: -0.1700
Data Index: 3289115 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0369. Min Range: -7.0369
Max Act: 6.5369. Min Act: -0.1700
Data Index: 5573881 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19