Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2548 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.9148. Min Act: -0.1699
Data Index: 5038420 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.7898. Min Act: -0.1700
Data Index: 871824 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.5398. Min Act: -0.1700
Data Index: 7234199 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.4148. Min Act: -0.1700
Data Index: 1961058 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.3523. Min Act: -0.1700
Data Index: 123587 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.3523. Min Act: -0.1700
Data Index: 2662355 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.2898. Min Act: -0.1700
Data Index: 8828033 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.2586. Min Act: -0.1700
Data Index: 509659 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.1336. Min Act: -0.1700
Data Index: 4017241 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.1648. Min Act: -0.1700
Data Index: 729831 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.1648. Min Act: -0.1700
Data Index: 4233534 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.1648. Min Act: -0.1700
Data Index: 3934583 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.1648. Min Act: -0.1700
Data Index: 6603198 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.1023. Min Act: -0.1700
Data Index: 547646 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.1023. Min Act: -0.1700
Data Index: 3264358 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.1023. Min Act: -0.1700
Data Index: 3743934 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.0711. Min Act: -0.1700
Data Index: 6279583 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.0398. Min Act: -0.1700
Data Index: 546696 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.0398. Min Act: -0.1700
Data Index: 2779335 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9148. Min Range: -7.9148
Max Act: 7.0398. Min Act: -0.1700
Data Index: 2513997 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19