Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.9346. Min Act: -0.1700
Data Index: 2932875 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.9034. Min Act: -0.1700
Data Index: 3733600 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.8721. Min Act: -0.1700
Data Index: 1557235 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.7784. Min Act: -0.1700
Data Index: 3564234 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.7784. Min Act: -0.1700
Data Index: 6552567 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.7159. Min Act: -0.1700
Data Index: 3642674 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.6221. Min Act: -0.1700
Data Index: 1456687 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.6221. Min Act: -0.1700
Data Index: 7200162 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.4971. Min Act: -0.1700
Data Index: 1419590 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.4034. Min Act: -0.1700
Data Index: 146545 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.3721. Min Act: -0.1700
Data Index: 946504 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.4034. Min Act: -0.1700
Data Index: 5688025 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.3721. Min Act: -0.1700
Data Index: 4041562 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.3721. Min Act: -0.1700
Data Index: 1402135 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.4034. Min Act: -0.1700
Data Index: 4169870 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.3409. Min Act: -0.1700
Data Index: 8039642 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.3409. Min Act: -0.1700
Data Index: 8365963 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.3096. Min Act: -0.1700
Data Index: 4236999 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.3096. Min Act: -0.1700
Data Index: 2002181 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9346. Min Range: -5.9346
Max Act: 5.3096. Min Act: -0.1700
Data Index: 6067205 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19