Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2522 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.5546. Min Act: -0.1700
Data Index: 743863 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.5234. Min Act: -0.1700
Data Index: 7019376 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.5234. Min Act: -0.1700
Data Index: 8188794 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.4921. Min Act: -0.1700
Data Index: 7228885 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.4609. Min Act: -0.1700
Data Index: 1507123 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3984. Min Act: -0.1700
Data Index: 531242 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.4609. Min Act: -0.1700
Data Index: 6669799 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.4296. Min Act: -0.1700
Data Index: 8763815 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3984. Min Act: -0.1700
Data Index: 6265909 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3984. Min Act: -0.1700
Data Index: 7714449 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3671. Min Act: -0.1700
Data Index: 3545143 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3359. Min Act: -0.1700
Data Index: 275957 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3046. Min Act: -0.1700
Data Index: 3086751 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3046. Min Act: -0.1700
Data Index: 6489540 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.3359. Min Act: -0.1700
Data Index: 4142050 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.2734. Min Act: -0.1700
Data Index: 6973206 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.2734. Min Act: -0.1700
Data Index: 5366551 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.2734. Min Act: -0.1700
Data Index: 7396217 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.2734. Min Act: -0.1700
Data Index: 5278942 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5546. Min Range: -5.5546
Max Act: 5.2734. Min Act: -0.1700
Data Index: 29691 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19