Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5907 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3624. Min Range: -5.3624
Max Act: 5.3624. Min Act: -0.1700
Data Index: 477890 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3624. Min Range: -5.3624
Max Act: 5.0499. Min Act: -0.1700
Data Index: 4072895 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3624. Min Range: -5.3624
Max Act: 5.0187. Min Act: -0.1700
Data Index: 6573742 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3624. Min Range: -5.3624
Max Act: 5.0187. Min Act: -0.1700
Data Index: 5179988 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.9562. Min Act: -0.1700
Data Index: 2782780 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.9249. Min Act: -0.1700
Data Index: 1141091 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.9249. Min Act: -0.1700
Data Index: 1141089 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.8937. Min Act: -0.1700
Data Index: 1100745 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.8937. Min Act: -0.1700
Data Index: 6753687 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.8937. Min Act: -0.1700
Data Index: 6119161 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.8624. Min Act: -0.1700
Data Index: 1909250 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.8624. Min Act: -0.1700
Data Index: 3853847 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.7999. Min Act: -0.1700
Data Index: 3980131 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.8312. Min Act: -0.1700
Data Index: 5252491 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.7999. Min Act: -0.1700
Data Index: 4072894 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.7999. Min Act: -0.1700
Data Index: 1441111 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.8312. Min Act: -0.1700
Data Index: 3218214 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.7687. Min Act: -0.1700
Data Index: 3491228 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.8312. Min Act: -0.1700
Data Index: 7771622 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3624. Min Range: -5.3624
Max Act: 4.7999. Min Act: -0.1700
Data Index: 1648278 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19