Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2728 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.7784. Min Act: -0.1700
Data Index: 2733473 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.7784. Min Act: -0.1700
Data Index: 3118309 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.5284. Min Act: -0.1700
Data Index: 6530367 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.5284. Min Act: -0.1700
Data Index: 3247947 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.5284. Min Act: -0.1700
Data Index: 5473218 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.5284. Min Act: -0.1700
Data Index: 7459450 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.4659. Min Act: -0.1700
Data Index: 1951687 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.4659. Min Act: -0.1700
Data Index: 8174632 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.4659. Min Act: -0.1700
Data Index: 1430259 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.4659. Min Act: -0.1700
Data Index: 1227553 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.4034. Min Act: -0.1700
Data Index: 6456924 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.4034. Min Act: -0.1700
Data Index: 8129393 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.4659. Min Act: -0.1700
Data Index: 7412752 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.4034. Min Act: -0.1700
Data Index: 4502974 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.3409. Min Act: -0.1700
Data Index: 7771262 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.3409. Min Act: -0.1700
Data Index: 7412750 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.3409. Min Act: -0.1700
Data Index: 2293041 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.3409. Min Act: -0.1700
Data Index: 3789947 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.3409. Min Act: -0.1700
Data Index: 3766300 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7784. Min Range: -9.7784
Max Act: 9.2784. Min Act: -0.1700
Data Index: 2094103 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19