Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2368 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0110. Min Range: -8.0110
Max Act: 8.0110. Min Act: -0.1700
Data Index: 7617715 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.9485. Min Act: -0.1700
Data Index: 7154503 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.8860. Min Act: -0.1700
Data Index: 2886669 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.8235. Min Act: -0.1700
Data Index: 889359 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.8235. Min Act: -0.1700
Data Index: 8825420 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.8235. Min Act: -0.1700
Data Index: 3800352 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.7610. Min Act: -0.1700
Data Index: 694641 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.7610. Min Act: -0.1700
Data Index: 8686887 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.7610. Min Act: -0.1700
Data Index: 997004 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.6985. Min Act: -0.1700
Data Index: 2721592 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.6985. Min Act: -0.1700
Data Index: 33870 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.6985. Min Act: -0.1700
Data Index: 4543142 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.6985. Min Act: -0.1700
Data Index: 2779436 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.5735. Min Act: -0.1700
Data Index: 6878119 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.6360. Min Act: -0.1700
Data Index: 5416004 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.6360. Min Act: -0.1700
Data Index: 17451 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.5735. Min Act: -0.1700
Data Index: 3480499 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.6360. Min Act: -0.1700
Data Index: 1600126 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.6360. Min Act: -0.1700
Data Index: 6317310 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0110. Min Range: -8.0110
Max Act: 7.5735. Min Act: -0.1700
Data Index: 1524718 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19