Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0683. Min Range: -6.0683
Max Act: 6.0683. Min Act: -0.1700
Data Index: 6116787 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.8808. Min Act: -0.1700
Data Index: 4597684 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.8496. Min Act: -0.1700
Data Index: 8243767 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.8183. Min Act: -0.1700
Data Index: 7170958 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.7558. Min Act: -0.1700
Data Index: 7166136 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.6933. Min Act: -0.1700
Data Index: 4115734 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.6621. Min Act: -0.1700
Data Index: 4482870 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.6308. Min Act: -0.1700
Data Index: 113714 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.6308. Min Act: -0.1700
Data Index: 3434303 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.6308. Min Act: -0.1700
Data Index: 5370849 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.6308. Min Act: -0.1700
Data Index: 1930128 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.6308. Min Act: -0.1700
Data Index: 4630453 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.5996. Min Act: -0.1700
Data Index: 8451484 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.5996. Min Act: -0.1700
Data Index: 3957220 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 5222625 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 2657037 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 3948368 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.5371. Min Act: -0.1700
Data Index: 1265335 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.5058. Min Act: -0.1700
Data Index: 3713481 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0683. Min Range: -6.0683
Max Act: 5.5371. Min Act: -0.1700
Data Index: 467772 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19