Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2158. Min Range: -7.2158
Max Act: 7.2158. Min Act: -0.1700
Data Index: 6119534 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.9970. Min Act: -0.1700
Data Index: 6860668 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.8720. Min Act: -0.1700
Data Index: 2763117 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.8408. Min Act: -0.1700
Data Index: 8111084 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.8095. Min Act: -0.1700
Data Index: 3521827 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.7158. Min Act: -0.1700
Data Index: 3927141 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.6845. Min Act: -0.1700
Data Index: 4588619 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.6220. Min Act: -0.1700
Data Index: 949682 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.6220. Min Act: -0.1700
Data Index: 3430641 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.6220. Min Act: -0.1700
Data Index: 5977327 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.6220. Min Act: -0.1700
Data Index: 159159 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.5908. Min Act: -0.1700
Data Index: 3458005 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.5908. Min Act: -0.1700
Data Index: 4052392 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.5595. Min Act: -0.1700
Data Index: 5626979 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.5595. Min Act: -0.1700
Data Index: 7796340 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.5283. Min Act: -0.1700
Data Index: 6465474 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.5283. Min Act: -0.1700
Data Index: 3701706 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.4970. Min Act: -0.1700
Data Index: 7051684 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.4970. Min Act: -0.1700
Data Index: 6761521 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2158. Min Range: -7.2158
Max Act: 6.4970. Min Act: -0.1700
Data Index: 8406308 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19