Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1465 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0075. Min Range: -7.0075
Max Act: 7.0075. Min Act: -0.1700
Data Index: 6998667 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.8200. Min Act: -0.1700
Data Index: 4157161 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.7575. Min Act: -0.1700
Data Index: 5530959 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.5700. Min Act: -0.1700
Data Index: 3065794 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.5700. Min Act: -0.1700
Data Index: 4953049 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.5075. Min Act: -0.1700
Data Index: 6144892 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.5075. Min Act: -0.1700
Data Index: 3854450 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.4450. Min Act: -0.1700
Data Index: 7562270 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.4137. Min Act: -0.1700
Data Index: 7092146 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.3825. Min Act: -0.1700
Data Index: 3463897 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.3825. Min Act: -0.1700
Data Index: 147789 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.3512. Min Act: -0.1700
Data Index: 7417435 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.3825. Min Act: -0.1700
Data Index: 8400659 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.3512. Min Act: -0.1700
Data Index: 8690852 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.3200. Min Act: -0.1700
Data Index: 11265 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.3512. Min Act: -0.1700
Data Index: 4515772 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.3825. Min Act: -0.1700
Data Index: 7056370 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.2887. Min Act: -0.1700
Data Index: 374696 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.3200. Min Act: -0.1700
Data Index: 5745805 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0075. Min Range: -7.0075
Max Act: 6.3200. Min Act: -0.1700
Data Index: 4008809 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19