Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5548 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.6286. Min Act: -0.1700
Data Index: 8013493 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.4411. Min Act: -0.1700
Data Index: 5022943 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.2536. Min Act: -0.1700
Data Index: 6541008 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.2223. Min Act: -0.1700
Data Index: 4111541 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.2223. Min Act: -0.1700
Data Index: 7352065 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.2223. Min Act: -0.1700
Data Index: 4281034 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.1910. Min Act: -0.1700
Data Index: 1903432 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.1910. Min Act: -0.1700
Data Index: 424681 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.1910. Min Act: -0.1700
Data Index: 7533887 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.1598. Min Act: -0.1700
Data Index: 2369073 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.1910. Min Act: -0.1700
Data Index: 5321819 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.1598. Min Act: -0.1700
Data Index: 7773729 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.1285. Min Act: -0.1700
Data Index: 206162 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.1285. Min Act: -0.1700
Data Index: 3354529 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.0973. Min Act: -0.1700
Data Index: 1247138 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.0973. Min Act: -0.1700
Data Index: 7369345 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.0973. Min Act: -0.1700
Data Index: 8115515 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.0660. Min Act: -0.1700
Data Index: 33521 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.0660. Min Act: -0.1700
Data Index: 2703725 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6286. Min Range: -4.6286
Max Act: 4.0660. Min Act: -0.1700
Data Index: 3263821 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19