Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5102 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6812. Min Act: -0.1700
Data Index: 7093895 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6343. Min Act: -0.1700
Data Index: 2243251 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.5717. Min Act: -0.1700
Data Index: 8526023 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.5873. Min Act: -0.1700
Data Index: 1944839 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.5560. Min Act: -0.1700
Data Index: 2885182 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.5403. Min Act: -0.1700
Data Index: 602189 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.5090. Min Act: -0.1700
Data Index: 4581303 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4777. Min Act: -0.1700
Data Index: 5236415 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4934. Min Act: -0.1700
Data Index: 2876982 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4777. Min Act: -0.1700
Data Index: 3002364 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4620. Min Act: -0.1700
Data Index: 4705537 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4464. Min Act: -0.1700
Data Index: 7780951 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4464. Min Act: -0.1700
Data Index: 7882276 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4464. Min Act: -0.1700
Data Index: 3863122 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.4307. Min Act: -0.1700
Data Index: 2962774 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.3837. Min Act: -0.1700
Data Index: 134155 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.3837. Min Act: -0.1700
Data Index: 6747084 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.3680. Min Act: -0.1700
Data Index: 1306682 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.3366. Min Act: -0.1700
Data Index: 1131349 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.3366. Min Act: -0.1700
Data Index: 4727243 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19