Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3307. Min Range: -7.3307
Max Act: 7.3307. Min Act: -0.1700
Data Index: 4586828 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3307. Min Range: -7.3307
Max Act: 7.2370. Min Act: -0.1700
Data Index: 2216603 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3307. Min Range: -7.3307
Max Act: 7.0495. Min Act: -0.1700
Data Index: 7961688 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.8932. Min Act: -0.1700
Data Index: 7081949 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.8932. Min Act: -0.1700
Data Index: 1274186 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.8932. Min Act: -0.1700
Data Index: 5907998 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.7682. Min Act: -0.1700
Data Index: 4957044 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.7370. Min Act: -0.1700
Data Index: 6312354 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.7370. Min Act: -0.1700
Data Index: 907077 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.6745. Min Act: -0.1700
Data Index: 8591339 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.7057. Min Act: -0.1700
Data Index: 2025488 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.7057. Min Act: -0.1700
Data Index: 2608761 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.6745. Min Act: -0.1700
Data Index: 2044512 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.6745. Min Act: -0.1700
Data Index: 6650651 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.6120. Min Act: -0.1700
Data Index: 8450803 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.6432. Min Act: -0.1700
Data Index: 4453417 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.6432. Min Act: -0.1700
Data Index: 844020 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.6120. Min Act: -0.1700
Data Index: 8633431 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.5807. Min Act: -0.1700
Data Index: 5100117 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3307. Min Range: -7.3307
Max Act: 6.5807. Min Act: -0.1700
Data Index: 5869789 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19