Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2677 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.7747. Min Act: -0.1700
Data Index: 2073735 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.7122. Min Act: -0.1700
Data Index: 5367360 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.7122. Min Act: -0.1700
Data Index: 6947755 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.6809. Min Act: -0.1700
Data Index: 6058239 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.6809. Min Act: -0.1700
Data Index: 911184 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.6809. Min Act: -0.1700
Data Index: 2312741 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.6809. Min Act: -0.1700
Data Index: 2309091 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.6809. Min Act: -0.1700
Data Index: 8270062 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.6809. Min Act: -0.1700
Data Index: 2291966 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.6497. Min Act: -0.1700
Data Index: 7207821 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.6497. Min Act: -0.1700
Data Index: 1297138 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.6809. Min Act: -0.1700
Data Index: 5003259 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.5872. Min Act: -0.1700
Data Index: 8314330 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.6184. Min Act: -0.1700
Data Index: 5625233 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.5872. Min Act: -0.1700
Data Index: 4616559 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.5872. Min Act: -0.1700
Data Index: 4952509 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.5872. Min Act: -0.1700
Data Index: 1354842 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.6184. Min Act: -0.1700
Data Index: 1987974 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.5872. Min Act: -0.1700
Data Index: 7115922 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7747. Min Range: -4.7747
Max Act: 4.5559. Min Act: -0.1700
Data Index: 5303121 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19