Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4300 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.8031. Min Act: -0.1700
Data Index: 7378749 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.5843. Min Act: -0.1700
Data Index: 4170979 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.4906. Min Act: -0.1700
Data Index: 7958323 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.3968. Min Act: -0.1700
Data Index: 2328770 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.3030. Min Act: -0.1700
Data Index: 1944245 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.2093. Min Act: -0.1700
Data Index: 8408205 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.2093. Min Act: -0.1700
Data Index: 5710921 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.2093. Min Act: -0.1700
Data Index: 5663609 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.2093. Min Act: -0.1700
Data Index: 5493856 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.1468. Min Act: -0.1700
Data Index: 3117031 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.1468. Min Act: -0.1700
Data Index: 3780393 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.1468. Min Act: -0.1700
Data Index: 5530571 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.1468. Min Act: -0.1700
Data Index: 5808628 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.1155. Min Act: -0.1700
Data Index: 1881224 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.1155. Min Act: -0.1700
Data Index: 7754765 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.1155. Min Act: -0.1700
Data Index: 1515684 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.0843. Min Act: -0.1700
Data Index: 3136905 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.0843. Min Act: -0.1700
Data Index: 1815710 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.0843. Min Act: -0.1700
Data Index: 2371193 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8031. Min Range: -4.8031
Max Act: 4.0530. Min Act: -0.1700
Data Index: 2619453 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19