Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5685 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.9343. Min Act: -0.1700
Data Index: 4028263 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.8718. Min Act: -0.1700
Data Index: 5998019 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.8718. Min Act: -0.1700
Data Index: 3522099 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.6843. Min Act: -0.1700
Data Index: 6107717 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.6843. Min Act: -0.1700
Data Index: 7490689 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.5593. Min Act: -0.1700
Data Index: 8215665 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.4343. Min Act: -0.1700
Data Index: 8648029 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.4343. Min Act: -0.1700
Data Index: 5447763 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.3718. Min Act: -0.1700
Data Index: 2561738 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.3093. Min Act: -0.1700
Data Index: 4201783 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.3093. Min Act: -0.1700
Data Index: 4651547 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.3093. Min Act: -0.1700
Data Index: 5577066 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.3093. Min Act: -0.1700
Data Index: 3364642 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.2468. Min Act: -0.1700
Data Index: 4288387 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.2468. Min Act: -0.1700
Data Index: 8364476 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.1843. Min Act: -0.1700
Data Index: 213920 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.1843. Min Act: -0.1700
Data Index: 6576232 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.0593. Min Act: -0.1700
Data Index: 6286274 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.1218. Min Act: -0.1700
Data Index: 7794747 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9343. Min Range: -12.9343
Max Act: 12.1218. Min Act: -0.1700
Data Index: 3798972 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19