Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4828 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2033. Min Range: -6.2033
Max Act: 6.2033. Min Act: -0.1700
Data Index: 6112991 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2033. Min Range: -6.2033
Max Act: 6.1408. Min Act: -0.1700
Data Index: 3666924 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.9846. Min Act: -0.1700
Data Index: 8577753 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.9846. Min Act: -0.1700
Data Index: 2118396 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.9533. Min Act: -0.1700
Data Index: 4820689 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.9533. Min Act: -0.1700
Data Index: 597078 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.8908. Min Act: -0.1700
Data Index: 2655691 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.8908. Min Act: -0.1700
Data Index: 5186135 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.8596. Min Act: -0.1700
Data Index: 1767003 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.8596. Min Act: -0.1700
Data Index: 7088570 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.8908. Min Act: -0.1700
Data Index: 702200 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.8283. Min Act: -0.1700
Data Index: 979019 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.8283. Min Act: -0.1700
Data Index: 3950441 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.8283. Min Act: -0.1700
Data Index: 1669432 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.7971. Min Act: -0.1700
Data Index: 2453147 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.7971. Min Act: -0.1700
Data Index: 6068872 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.7971. Min Act: -0.1700
Data Index: 2794138 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.7971. Min Act: -0.1700
Data Index: 1650795 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.7971. Min Act: -0.1700
Data Index: 5199092 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2033. Min Range: -6.2033
Max Act: 5.7971. Min Act: -0.1700
Data Index: 428890 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19