Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3612 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1702. Min Range: -4.1702
Max Act: 4.1702. Min Act: -0.1700
Data Index: 829950 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1702. Min Range: -4.1702
Max Act: 4.0452. Min Act: -0.1700
Data Index: 7666445 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.9514. Min Act: -0.1700
Data Index: 1602202 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.9514. Min Act: -0.1700
Data Index: 4566859 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.9201. Min Act: -0.1700
Data Index: 1763584 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8889. Min Act: -0.1700
Data Index: 4830545 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8732. Min Act: -0.1700
Data Index: 8407048 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8889. Min Act: -0.1700
Data Index: 1421291 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8889. Min Act: -0.1700
Data Index: 7927245 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8732. Min Act: -0.1700
Data Index: 6259290 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8576. Min Act: -0.1700
Data Index: 8643529 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8420. Min Act: -0.1700
Data Index: 8725152 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8420. Min Act: -0.1700
Data Index: 1052325 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8263. Min Act: -0.1700
Data Index: 8449665 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8263. Min Act: -0.1700
Data Index: 8340749 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8107. Min Act: -0.1700
Data Index: 1258879 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8107. Min Act: -0.1700
Data Index: 5375665 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.7951. Min Act: -0.1700
Data Index: 1984996 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.7638. Min Act: -0.1700
Data Index: 7847507 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.7794. Min Act: -0.1700
Data Index: 5480912 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19