Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4302 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2452. Min Range: -10.2452
Max Act: 10.2452. Min Act: -0.1700
Data Index: 3371030 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2452. Min Range: -10.2452
Max Act: 10.1827. Min Act: -0.1700
Data Index: 6715161 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.9327. Min Act: -0.1700
Data Index: 8228184 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.8077. Min Act: -0.1700
Data Index: 4122609 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.8077. Min Act: -0.1700
Data Index: 1467111 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.7452. Min Act: -0.1700
Data Index: 1892777 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.6827. Min Act: -0.1700
Data Index: 5930942 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.6827. Min Act: -0.1700
Data Index: 2935184 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.6827. Min Act: -0.1700
Data Index: 2003881 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.6202. Min Act: -0.1700
Data Index: 1470980 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.6202. Min Act: -0.1700
Data Index: 8740210 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.5577. Min Act: -0.1700
Data Index: 1463197 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.5577. Min Act: -0.1700
Data Index: 6412049 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.5577. Min Act: -0.1700
Data Index: 2212364 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.4952. Min Act: -0.1700
Data Index: 6487588 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.4952. Min Act: -0.1700
Data Index: 184177 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.3077. Min Act: -0.1700
Data Index: 7184955 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.3702. Min Act: -0.1700
Data Index: 3823601 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.3702. Min Act: -0.1700
Data Index: 4228274 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2452. Min Range: -10.2452
Max Act: 9.3702. Min Act: -0.1700
Data Index: 8610051 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19