Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3281 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1173. Min Range: -4.1173
Max Act: 4.1173. Min Act: -0.1700
Data Index: 220939 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1173. Min Range: -4.1173
Max Act: 4.1173. Min Act: -0.1700
Data Index: 2075651 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1173. Min Range: -4.1173
Max Act: 4.0548. Min Act: -0.1700
Data Index: 1213264 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1173. Min Range: -4.1173
Max Act: 4.0235. Min Act: -0.1700
Data Index: 7973568 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.9922. Min Act: -0.1700
Data Index: 1690924 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.9922. Min Act: -0.1700
Data Index: 8368549 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.9922. Min Act: -0.1700
Data Index: 7611408 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.9610. Min Act: -0.1700
Data Index: 6780673 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.9610. Min Act: -0.1700
Data Index: 616699 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.9610. Min Act: -0.1700
Data Index: 1638335 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.9610. Min Act: -0.1700
Data Index: 7340493 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.9297. Min Act: -0.1700
Data Index: 3663786 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.9610. Min Act: -0.1700
Data Index: 4082839 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.9297. Min Act: -0.1700
Data Index: 5011758 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.9297. Min Act: -0.1700
Data Index: 5401307 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.9297. Min Act: -0.1700
Data Index: 5834705 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.8985. Min Act: -0.1700
Data Index: 1813877 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.8985. Min Act: -0.1700
Data Index: 6500707 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.8985. Min Act: -0.1700
Data Index: 947716 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1173. Min Range: -4.1173
Max Act: 3.8985. Min Act: -0.1700
Data Index: 2102323 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19