Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5088 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0467. Min Range: -11.0467
Max Act: 11.0467. Min Act: -0.1700
Data Index: 7532877 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.9217. Min Act: -0.1700
Data Index: 8774612 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.8592. Min Act: -0.1700
Data Index: 678958 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.7967. Min Act: -0.1700
Data Index: 7927559 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.5467. Min Act: -0.1700
Data Index: 2913495 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.4217. Min Act: -0.1700
Data Index: 6143668 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.4842. Min Act: -0.1700
Data Index: 4677872 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.4842. Min Act: -0.1700
Data Index: 5465356 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.3592. Min Act: -0.1700
Data Index: 6612440 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.3592. Min Act: -0.1700
Data Index: 2049501 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.3592. Min Act: -0.1700
Data Index: 6423198 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.3592. Min Act: -0.1700
Data Index: 3768 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.2967. Min Act: -0.1700
Data Index: 8774613 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.2967. Min Act: -0.1700
Data Index: 8826902 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.2967. Min Act: -0.1700
Data Index: 2447059 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.1717. Min Act: -0.1700
Data Index: 2034965 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.1717. Min Act: -0.1700
Data Index: 54682 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.1092. Min Act: -0.1700
Data Index: 4990003 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.1092. Min Act: -0.1700
Data Index: 4989992 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0467. Min Range: -11.0467
Max Act: 10.1092. Min Act: -0.1700
Data Index: 6423205 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19