Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5336 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0057. Min Range: -5.0057
Max Act: 5.0057. Min Act: -0.1700
Data Index: 6231232 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.8494. Min Act: -0.1700
Data Index: 3021250 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.8494. Min Act: -0.1700
Data Index: 6213842 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.8494. Min Act: -0.1700
Data Index: 657611 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.8182. Min Act: -0.1700
Data Index: 3374008 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.8182. Min Act: -0.1700
Data Index: 8168030 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7869. Min Act: -0.1700
Data Index: 6006875 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7869. Min Act: -0.1700
Data Index: 616351 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7869. Min Act: -0.1700
Data Index: 5833772 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7869. Min Act: -0.1700
Data Index: 392062 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7869. Min Act: -0.1700
Data Index: 93124 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7557. Min Act: -0.1700
Data Index: 5776714 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7244. Min Act: -0.1700
Data Index: 2501019 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7557. Min Act: -0.1700
Data Index: 661993 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7557. Min Act: -0.1700
Data Index: 5588714 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7869. Min Act: -0.1700
Data Index: 6961244 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.6932. Min Act: -0.1700
Data Index: 7613692 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.6932. Min Act: -0.1700
Data Index: 853913 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.6932. Min Act: -0.1700
Data Index: 3094651 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.6932. Min Act: -0.1700
Data Index: 1442215 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19