Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2652 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0607. Min Range: -9.0607
Max Act: 9.0607. Min Act: -0.1700
Data Index: 5425978 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.7482. Min Act: -0.1700
Data Index: 4172368 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.4982. Min Act: -0.1700
Data Index: 198509 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.4982. Min Act: -0.1700
Data Index: 7678191 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.3107. Min Act: -0.1700
Data Index: 2461699 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.3107. Min Act: -0.1700
Data Index: 8456316 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.3107. Min Act: -0.1700
Data Index: 3207273 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.2795. Min Act: -0.1700
Data Index: 1793217 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.1232. Min Act: -0.1700
Data Index: 589616 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.1232. Min Act: -0.1700
Data Index: 961449 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.0607. Min Act: -0.1700
Data Index: 553728 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.0295. Min Act: -0.1700
Data Index: 1562758 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.0295. Min Act: -0.1700
Data Index: 883400 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.0295. Min Act: -0.1700
Data Index: 4567869 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0607. Min Range: -9.0607
Max Act: 8.0295. Min Act: -0.1700
Data Index: 8346380 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0607. Min Range: -9.0607
Max Act: 7.9357. Min Act: -0.1700
Data Index: 944971 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0607. Min Range: -9.0607
Max Act: 7.9357. Min Act: -0.1700
Data Index: 6063548 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0607. Min Range: -9.0607
Max Act: 7.9045. Min Act: -0.1700
Data Index: 7945851 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0607. Min Range: -9.0607
Max Act: 7.8732. Min Act: -0.1700
Data Index: 8397309 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0607. Min Range: -9.0607
Max Act: 7.8732. Min Act: -0.1700
Data Index: 4157220 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19