Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 512 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.5984. Min Act: -0.1700
Data Index: 2565956 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.5984. Min Act: -0.1700
Data Index: 2565955 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.5359. Min Act: -0.1700
Data Index: 15594 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.4422. Min Act: -0.1700
Data Index: 4984224 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.4422. Min Act: -0.1700
Data Index: 2333466 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.4422. Min Act: -0.1700
Data Index: 6477245 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.4422. Min Act: -0.1700
Data Index: 4229734 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.3797. Min Act: -0.1700
Data Index: 8360176 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.4109. Min Act: -0.1700
Data Index: 2514097 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.4109. Min Act: -0.1700
Data Index: 1309040 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.4109. Min Act: -0.1700
Data Index: 1456045 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.4109. Min Act: -0.1700
Data Index: 4237419 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.3484. Min Act: -0.1700
Data Index: 5045478 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.3797. Min Act: -0.1700
Data Index: 7574266 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.3484. Min Act: -0.1700
Data Index: 2831292 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.3484. Min Act: -0.1700
Data Index: 787326 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.3172. Min Act: -0.1700
Data Index: 8002282 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.3172. Min Act: -0.1700
Data Index: 1750999 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.2859. Min Act: -0.1700
Data Index: 5367776 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5984. Min Range: -5.5984
Max Act: 5.2859. Min Act: -0.1700
Data Index: 1594548 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19