Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4673 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3232. Min Range: -10.3232
Max Act: 10.3232. Min Act: -0.1700
Data Index: 5177892 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.8857. Min Act: -0.1700
Data Index: 1491238 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.8857. Min Act: -0.1700
Data Index: 6170218 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.8857. Min Act: -0.1700
Data Index: 1300210 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.8232. Min Act: -0.1700
Data Index: 2738765 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.8232. Min Act: -0.1700
Data Index: 1258717 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.8232. Min Act: -0.1700
Data Index: 88462 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.8232. Min Act: -0.1700
Data Index: 7973464 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.7607. Min Act: -0.1700
Data Index: 5687622 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.6982. Min Act: -0.1700
Data Index: 3053108 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.7607. Min Act: -0.1700
Data Index: 5837144 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.7607. Min Act: -0.1700
Data Index: 1427757 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.7607. Min Act: -0.1700
Data Index: 7144092 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.6357. Min Act: -0.1700
Data Index: 8447221 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.6982. Min Act: -0.1700
Data Index: 8094452 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.6982. Min Act: -0.1700
Data Index: 899935 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.6982. Min Act: -0.1700
Data Index: 6871287 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.6982. Min Act: -0.1700
Data Index: 5209606 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.6982. Min Act: -0.1700
Data Index: 6484700 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3232. Min Range: -10.3232
Max Act: 9.6357. Min Act: -0.1700
Data Index: 4747515 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19