Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 524 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0597. Min Range: -4.0597
Max Act: 4.0597. Min Act: -0.1700
Data Index: 6134924 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.9347. Min Act: -0.1700
Data Index: 4391928 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.8721. Min Act: -0.1700
Data Index: 7987920 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.8721. Min Act: -0.1700
Data Index: 2220043 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.8721. Min Act: -0.1700
Data Index: 976872 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.7783. Min Act: -0.1700
Data Index: 376116 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.8096. Min Act: -0.1700
Data Index: 1109748 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.7783. Min Act: -0.1700
Data Index: 5135234 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.8096. Min Act: -0.1700
Data Index: 7118 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.7783. Min Act: -0.1700
Data Index: 447510 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.7783. Min Act: -0.1700
Data Index: 7454909 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.7783. Min Act: -0.1700
Data Index: 103804 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.7783. Min Act: -0.1700
Data Index: 1463204 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.7470. Min Act: -0.1700
Data Index: 5286427 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.7470. Min Act: -0.1700
Data Index: 4585183 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.7470. Min Act: -0.1700
Data Index: 2286221 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.7470. Min Act: -0.1700
Data Index: 779109 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.7314. Min Act: -0.1700
Data Index: 6786546 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.7314. Min Act: -0.1700
Data Index: 7813992 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0597. Min Range: -4.0597
Max Act: 3.7470. Min Act: -0.1700
Data Index: 6322735 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19