Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 598 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3776. Min Range: -8.3776
Max Act: 8.3776. Min Act: -0.1700
Data Index: 95063 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3776. Min Range: -8.3776
Max Act: 8.1276. Min Act: -0.1700
Data Index: 6158029 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3776. Min Range: -8.3776
Max Act: 8.1276. Min Act: -0.1700
Data Index: 3095807 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3776. Min Range: -8.3776
Max Act: 8.0651. Min Act: -0.1700
Data Index: 3106190 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3776. Min Range: -8.3776
Max Act: 8.0651. Min Act: -0.1700
Data Index: 5167928 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3776. Min Range: -8.3776
Max Act: 8.0026. Min Act: -0.1700
Data Index: 1889107 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3776. Min Range: -8.3776
Max Act: 8.0026. Min Act: -0.1700
Data Index: 461915 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3776. Min Range: -8.3776
Max Act: 7.8776. Min Act: -0.1700
Data Index: 536825 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3776. Min Range: -8.3776
Max Act: 7.8464. Min Act: -0.1700
Data Index: 1892919 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3776. Min Range: -8.3776
Max Act: 7.8151. Min Act: -0.1700
Data Index: 205968 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3776. Min Range: -8.3776
Max Act: 7.8151. Min Act: -0.1700
Data Index: 8070741 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3776. Min Range: -8.3776
Max Act: 7.7526. Min Act: -0.1700
Data Index: 7416265 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3776. Min Range: -8.3776
Max Act: 7.7214. Min Act: -0.1700
Data Index: 6783748 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3776. Min Range: -8.3776
Max Act: 7.7214. Min Act: -0.1700
Data Index: 2721961 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3776. Min Range: -8.3776
Max Act: 7.7214. Min Act: -0.1700
Data Index: 6684561 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3776. Min Range: -8.3776
Max Act: 7.6589. Min Act: -0.1700
Data Index: 8262755 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3776. Min Range: -8.3776
Max Act: 7.6589. Min Act: -0.1700
Data Index: 279327 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3776. Min Range: -8.3776
Max Act: 7.5964. Min Act: -0.1700
Data Index: 2912905 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3776. Min Range: -8.3776
Max Act: 7.5964. Min Act: -0.1700
Data Index: 8206975 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3776. Min Range: -8.3776
Max Act: 7.5651. Min Act: -0.1700
Data Index: 169493 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19