Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.5884. Min Act: -0.1700
Data Index: 4797041 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.5571. Min Act: -0.1700
Data Index: 3719045 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.5259. Min Act: -0.1700
Data Index: 7119192 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.4946. Min Act: -0.1700
Data Index: 2486296 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.4946. Min Act: -0.1699
Data Index: 4110032 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.4634. Min Act: -0.1700
Data Index: 6036135 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.4009. Min Act: -0.1700
Data Index: 4172975 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.4009. Min Act: -0.1700
Data Index: 7886559 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.4009. Min Act: -0.1700
Data Index: 2861843 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.3696. Min Act: -0.1700
Data Index: 3719046 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.3696. Min Act: -0.1700
Data Index: 7049661 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.3071. Min Act: -0.1700
Data Index: 569880 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.3384. Min Act: -0.1700
Data Index: 3719044 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.3071. Min Act: -0.1700
Data Index: 7049666 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.3384. Min Act: -0.1700
Data Index: 7510208 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.3071. Min Act: -0.1700
Data Index: 7049679 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.2759. Min Act: -0.1700
Data Index: 4919840 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.2759. Min Act: -0.1700
Data Index: 7049671 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.3071. Min Act: -0.1700
Data Index: 748609 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5884. Min Range: -5.5884
Max Act: 5.2446. Min Act: -0.1700
Data Index: 4333536 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19