Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.5594. Min Act: -0.1700
Data Index: 2371358 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.4969. Min Act: -0.1700
Data Index: 476030 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.4656. Min Act: -0.1700
Data Index: 669498 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.3094. Min Act: -0.1700
Data Index: 3025874 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.2156. Min Act: -0.1700
Data Index: 1483168 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.1219. Min Act: -0.1700
Data Index: 6749466 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.1531. Min Act: -0.1700
Data Index: 8038806 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.1531. Min Act: -0.1700
Data Index: 2197950 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.1219. Min Act: -0.1700
Data Index: 8191593 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.1219. Min Act: -0.1700
Data Index: 3287275 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.1219. Min Act: -0.1700
Data Index: 2738798 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.0906. Min Act: -0.1700
Data Index: 4749547 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.0906. Min Act: -0.1700
Data Index: 6367049 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.0906. Min Act: -0.1700
Data Index: 3866501 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.0594. Min Act: -0.1700
Data Index: 1208980 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.0594. Min Act: -0.1700
Data Index: 5496711 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5594. Min Range: -7.5594
Max Act: 7.0281. Min Act: -0.1700
Data Index: 3405119 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5594. Min Range: -7.5594
Max Act: 6.9969. Min Act: -0.1700
Data Index: 516406 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5594. Min Range: -7.5594
Max Act: 6.9969. Min Act: -0.1700
Data Index: 2552015 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5594. Min Range: -7.5594
Max Act: 6.9656. Min Act: -0.1700
Data Index: 1486991 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19