Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3832 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2027. Min Range: -6.2027
Max Act: 6.2027. Min Act: -0.1700
Data Index: 8386539 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2027. Min Range: -6.2027
Max Act: 6.0465. Min Act: -0.1700
Data Index: 2196675 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.9840. Min Act: -0.1700
Data Index: 8004436 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.9215. Min Act: -0.1700
Data Index: 5833249 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.8902. Min Act: -0.1700
Data Index: 8556553 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.9215. Min Act: -0.1700
Data Index: 7115482 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.8277. Min Act: -0.1700
Data Index: 5508396 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.8277. Min Act: -0.1700
Data Index: 8691880 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.8277. Min Act: -0.1700
Data Index: 7305953 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.7652. Min Act: -0.1700
Data Index: 4996896 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.7965. Min Act: -0.1700
Data Index: 1957082 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.8277. Min Act: -0.1700
Data Index: 502387 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.7965. Min Act: -0.1700
Data Index: 3214743 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.7965. Min Act: -0.1700
Data Index: 7030556 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.7340. Min Act: -0.1700
Data Index: 8496482 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.7340. Min Act: -0.1700
Data Index: 3365949 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.7027. Min Act: -0.1700
Data Index: 1473580 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.7027. Min Act: -0.1700
Data Index: 477300 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.7027. Min Act: -0.1700
Data Index: 431986 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2027. Min Range: -6.2027
Max Act: 5.7027. Min Act: -0.1700
Data Index: 8152129 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19