Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1489 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.7940. Min Act: -0.1700
Data Index: 8748361 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.6220. Min Act: -0.1700
Data Index: 7521214 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.6220. Min Act: -0.1700
Data Index: 3798121 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.6220. Min Act: -0.1700
Data Index: 5463549 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5750. Min Act: -0.1700
Data Index: 1690349 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5594. Min Act: -0.1700
Data Index: 6152337 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5437. Min Act: -0.1700
Data Index: 8785023 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5437. Min Act: -0.1700
Data Index: 5527044 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5437. Min Act: -0.1700
Data Index: 2914533 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5124. Min Act: -0.1700
Data Index: 8469861 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5124. Min Act: -0.1700
Data Index: 3476415 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5124. Min Act: -0.1700
Data Index: 5995544 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4967. Min Act: -0.1700
Data Index: 7476324 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4811. Min Act: -0.1700
Data Index: 6373066 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4811. Min Act: -0.1700
Data Index: 8254479 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4811. Min Act: -0.1700
Data Index: 1125698 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4811. Min Act: -0.1700
Data Index: 5862108 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4811. Min Act: -0.1700
Data Index: 3355810 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4654. Min Act: -0.1700
Data Index: 2528700 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4654. Min Act: -0.1700
Data Index: 3492057 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19