Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6235 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.8362. Min Act: -0.1700
Data Index: 1170065 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.5862. Min Act: -0.1700
Data Index: 5100898 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.4612. Min Act: -0.1700
Data Index: 8449124 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.3987. Min Act: -0.1700
Data Index: 8767923 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.3362. Min Act: -0.1700
Data Index: 7479483 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.2112. Min Act: -0.1700
Data Index: 2710813 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.1487. Min Act: -0.1700
Data Index: 1172684 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.1487. Min Act: -0.1700
Data Index: 2026414 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.0862. Min Act: -0.1700
Data Index: 5663992 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.1487. Min Act: -0.1700
Data Index: 5354664 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.0862. Min Act: -0.1700
Data Index: 1387584 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.0862. Min Act: -0.1700
Data Index: 6280459 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.0862. Min Act: -0.1700
Data Index: 3928826 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.1487. Min Act: -0.1700
Data Index: 8498143 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.0862. Min Act: -0.1700
Data Index: 6029408 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.0862. Min Act: -0.1700
Data Index: 5077596 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.0237. Min Act: -0.1700
Data Index: 6601988 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.0237. Min Act: -0.1700
Data Index: 1825948 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8362. Min Range: -10.8362
Max Act: 10.0237. Min Act: -0.1700
Data Index: 6614486 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8362. Min Range: -10.8362
Max Act: 9.9612. Min Act: -0.1700
Data Index: 5366673 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19