Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2570 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.8372. Min Act: -0.1700
Data Index: 8472244 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.7435. Min Act: -0.1700
Data Index: 6384478 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.7122. Min Act: -0.1700
Data Index: 341080 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.6185. Min Act: -0.1700
Data Index: 5255032 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.6185. Min Act: -0.1700
Data Index: 4733445 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.5872. Min Act: -0.1700
Data Index: 64591 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.5872. Min Act: -0.1700
Data Index: 4076445 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.5872. Min Act: -0.1700
Data Index: 1295951 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.5872. Min Act: -0.1700
Data Index: 560130 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.5247. Min Act: -0.1700
Data Index: 4771331 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.5247. Min Act: -0.1700
Data Index: 6795914 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.4935. Min Act: -0.1700
Data Index: 8259861 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.4935. Min Act: -0.1700
Data Index: 438484 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.4622. Min Act: -0.1700
Data Index: 2562107 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.4622. Min Act: -0.1700
Data Index: 3662099 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.4622. Min Act: -0.1700
Data Index: 1473551 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.4622. Min Act: -0.1700
Data Index: 5140828 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.4622. Min Act: -0.1700
Data Index: 4890790 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.4622. Min Act: -0.1700
Data Index: 5476374 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8372. Min Range: -6.8372
Max Act: 6.4622. Min Act: -0.1700
Data Index: 3404504 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19