Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3323 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3113. Min Range: -5.3113
Max Act: 5.3113. Min Act: -0.1700
Data Index: 7673286 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3113. Min Range: -5.3113
Max Act: 5.2175. Min Act: -0.1700
Data Index: 4095068 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3113. Min Range: -5.3113
Max Act: 5.2175. Min Act: -0.1700
Data Index: 416767 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3113. Min Range: -5.3113
Max Act: 5.0613. Min Act: -0.1700
Data Index: 1356897 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3113. Min Range: -5.3113
Max Act: 5.0300. Min Act: -0.1700
Data Index: 2574297 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.9675. Min Act: -0.1700
Data Index: 1601118 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.9675. Min Act: -0.1700
Data Index: 3248232 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.9988. Min Act: -0.1700
Data Index: 3432664 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.9675. Min Act: -0.1700
Data Index: 4605679 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.9675. Min Act: -0.1700
Data Index: 4226944 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.9363. Min Act: -0.1700
Data Index: 4613996 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.8738. Min Act: -0.1700
Data Index: 629587 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.9050. Min Act: -0.1700
Data Index: 2056435 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.8738. Min Act: -0.1700
Data Index: 1504522 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.8738. Min Act: -0.1700
Data Index: 4150745 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.8738. Min Act: -0.1700
Data Index: 1012344 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.8425. Min Act: -0.1700
Data Index: 1126966 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.8425. Min Act: -0.1700
Data Index: 1143510 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.8738. Min Act: -0.1700
Data Index: 3158682 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3113. Min Range: -5.3113
Max Act: 4.8113. Min Act: -0.1700
Data Index: 5313070 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19