Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4974 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0680. Min Range: -5.0680
Max Act: 5.0680. Min Act: -0.1700
Data Index: 2049990 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.8805. Min Act: -0.1700
Data Index: 4689781 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.6305. Min Act: -0.1700
Data Index: 5425609 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5992. Min Act: -0.1700
Data Index: 6012307 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5680. Min Act: -0.1700
Data Index: 5677122 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5680. Min Act: -0.1700
Data Index: 6833670 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5367. Min Act: -0.1700
Data Index: 3094182 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5367. Min Act: -0.1700
Data Index: 2070031 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5367. Min Act: -0.1700
Data Index: 6045741 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5367. Min Act: -0.1700
Data Index: 2844028 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5367. Min Act: -0.1700
Data Index: 3821084 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.4742. Min Act: -0.1700
Data Index: 3757587 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5055. Min Act: -0.1700
Data Index: 4724947 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5055. Min Act: -0.1700
Data Index: 777944 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5055. Min Act: -0.1700
Data Index: 3789394 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5367. Min Act: -0.1700
Data Index: 522683 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5055. Min Act: -0.1700
Data Index: 5838238 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5055. Min Act: -0.1700
Data Index: 3495220 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.5055. Min Act: -0.1700
Data Index: 5241473 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0680. Min Range: -5.0680
Max Act: 4.4742. Min Act: -0.1700
Data Index: 1706701 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19