Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3395 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2702. Min Range: -5.2702
Max Act: 5.2702. Min Act: -0.1700
Data Index: 2475459 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.9889. Min Act: -0.1700
Data Index: 752876 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.9577. Min Act: -0.1700
Data Index: 8059101 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.9264. Min Act: -0.1700
Data Index: 752875 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.9264. Min Act: -0.1700
Data Index: 5102888 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.8952. Min Act: -0.1700
Data Index: 16290 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.8639. Min Act: -0.1700
Data Index: 5837053 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.8639. Min Act: -0.1700
Data Index: 96961 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.8327. Min Act: -0.1700
Data Index: 8498895 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.7702. Min Act: -0.1700
Data Index: 1014067 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.7389. Min Act: -0.1700
Data Index: 1317862 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.7389. Min Act: -0.1700
Data Index: 1272235 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.7389. Min Act: -0.1700
Data Index: 7900183 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.7077. Min Act: -0.1700
Data Index: 8828969 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.7077. Min Act: -0.1700
Data Index: 1127590 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.7077. Min Act: -0.1700
Data Index: 3926213 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.7077. Min Act: -0.1700
Data Index: 5048660 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.6764. Min Act: -0.1700
Data Index: 1212112 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.6764. Min Act: -0.1700
Data Index: 7513351 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2702. Min Range: -5.2702
Max Act: 4.6452. Min Act: -0.1700
Data Index: 2790213 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19