Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4610 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.4967. Min Act: -0.1700
Data Index: 1534091 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.4030. Min Act: -0.1700
Data Index: 5248836 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.4030. Min Act: -0.1700
Data Index: 2156648 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.4030. Min Act: -0.1700
Data Index: 4521774 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.2467. Min Act: -0.1700
Data Index: 3651752 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.1842. Min Act: -0.1700
Data Index: 1163841 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.1842. Min Act: -0.1700
Data Index: 7549103 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.1217. Min Act: -0.1700
Data Index: 2734770 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.1217. Min Act: -0.1700
Data Index: 239311 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.0905. Min Act: -0.1700
Data Index: 6342607 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.0905. Min Act: -0.1700
Data Index: 8574010 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.0592. Min Act: -0.1700
Data Index: 797355 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.0592. Min Act: -0.1700
Data Index: 4510975 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.0592. Min Act: -0.1700
Data Index: 7096430 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.0280. Min Act: -0.1700
Data Index: 1499668 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.0280. Min Act: -0.1700
Data Index: 1978471 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4967. Min Range: -5.4967
Max Act: 4.9967. Min Act: -0.1700
Data Index: 1163840 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.0280. Min Act: -0.1700
Data Index: 5358710 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.0280. Min Act: -0.1700
Data Index: 5942891 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.0280. Min Act: -0.1700
Data Index: 6766157 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19