Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 928 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2119. Min Range: -6.2119
Max Act: 6.2119. Min Act: -0.1700
Data Index: 3192827 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2119. Min Range: -6.2119
Max Act: 6.2119. Min Act: -0.1700
Data Index: 844789 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2119. Min Range: -6.2119
Max Act: 6.1807. Min Act: -0.1700
Data Index: 7720581 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2119. Min Range: -6.2119
Max Act: 6.1494. Min Act: -0.1700
Data Index: 4277075 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2119. Min Range: -6.2119
Max Act: 6.1807. Min Act: -0.1700
Data Index: 2866214 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2119. Min Range: -6.2119
Max Act: 6.1494. Min Act: -0.1700
Data Index: 7663989 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2119. Min Range: -6.2119
Max Act: 6.1182. Min Act: -0.1700
Data Index: 5463816 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2119. Min Range: -6.2119
Max Act: 6.1182. Min Act: -0.1700
Data Index: 4871250 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2119. Min Range: -6.2119
Max Act: 6.0869. Min Act: -0.1700
Data Index: 3052660 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2119. Min Range: -6.2119
Max Act: 6.0869. Min Act: -0.1700
Data Index: 169486 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2119. Min Range: -6.2119
Max Act: 6.0244. Min Act: -0.1700
Data Index: 3386958 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2119. Min Range: -6.2119
Max Act: 6.0244. Min Act: -0.1700
Data Index: 530044 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2119. Min Range: -6.2119
Max Act: 5.9619. Min Act: -0.1700
Data Index: 7213523 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2119. Min Range: -6.2119
Max Act: 5.9619. Min Act: -0.1700
Data Index: 5566417 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2119. Min Range: -6.2119
Max Act: 5.9619. Min Act: -0.1700
Data Index: 1853269 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2119. Min Range: -6.2119
Max Act: 5.9619. Min Act: -0.1700
Data Index: 5492382 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2119. Min Range: -6.2119
Max Act: 5.9307. Min Act: -0.1700
Data Index: 955566 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2119. Min Range: -6.2119
Max Act: 5.9307. Min Act: -0.1700
Data Index: 2914865 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2119. Min Range: -6.2119
Max Act: 5.9307. Min Act: -0.1700
Data Index: 5716626 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2119. Min Range: -6.2119
Max Act: 5.8994. Min Act: -0.1700
Data Index: 2260481 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19