Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4567 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.7870. Min Act: -0.1700
Data Index: 5474452 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.7245. Min Act: -0.1700
Data Index: 6274334 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.7870. Min Act: -0.1700
Data Index: 6731922 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.6933. Min Act: -0.1700
Data Index: 1386879 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5683. Min Act: -0.1700
Data Index: 4010657 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5995. Min Act: -0.1700
Data Index: 2235482 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5683. Min Act: -0.1700
Data Index: 7037207 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5683. Min Act: -0.1700
Data Index: 300368 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5683. Min Act: -0.1700
Data Index: 7632790 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5683. Min Act: -0.1700
Data Index: 7645257 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5683. Min Act: -0.1700
Data Index: 8085641 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5683. Min Act: -0.1700
Data Index: 3470263 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5370. Min Act: -0.1700
Data Index: 1410938 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5370. Min Act: -0.1700
Data Index: 1466915 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5683. Min Act: -0.1700
Data Index: 1126785 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5683. Min Act: -0.1700
Data Index: 6099031 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5683. Min Act: -0.1700
Data Index: 2728257 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5683. Min Act: -0.1700
Data Index: 4997872 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5683. Min Act: -0.1700
Data Index: 4008119 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7870. Min Range: -6.7870
Max Act: 6.5683. Min Act: -0.1700
Data Index: 6651707 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19