Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4968 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3884. Min Range: -7.3884
Max Act: 7.3884. Min Act: -0.1700
Data Index: 4488859 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3884. Min Range: -7.3884
Max Act: 7.3571. Min Act: -0.1700
Data Index: 7263754 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3884. Min Range: -7.3884
Max Act: 7.2634. Min Act: -0.1700
Data Index: 2812014 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3884. Min Range: -7.3884
Max Act: 7.2321. Min Act: -0.1700
Data Index: 4247027 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3884. Min Range: -7.3884
Max Act: 7.1384. Min Act: -0.1700
Data Index: 4890507 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3884. Min Range: -7.3884
Max Act: 7.1071. Min Act: -0.1700
Data Index: 44104 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3884. Min Range: -7.3884
Max Act: 7.0446. Min Act: -0.1700
Data Index: 1707909 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3884. Min Range: -7.3884
Max Act: 7.0134. Min Act: -0.1700
Data Index: 7731558 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3884. Min Range: -7.3884
Max Act: 7.0134. Min Act: -0.1700
Data Index: 8796287 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3884. Min Range: -7.3884
Max Act: 7.0134. Min Act: -0.1700
Data Index: 954224 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3884. Min Range: -7.3884
Max Act: 6.9509. Min Act: -0.1700
Data Index: 1395347 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3884. Min Range: -7.3884
Max Act: 6.9509. Min Act: -0.1700
Data Index: 4076252 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3884. Min Range: -7.3884
Max Act: 6.9196. Min Act: -0.1700
Data Index: 3665539 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3884. Min Range: -7.3884
Max Act: 6.9196. Min Act: -0.1700
Data Index: 5746654 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3884. Min Range: -7.3884
Max Act: 6.9196. Min Act: -0.1700
Data Index: 1708493 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3884. Min Range: -7.3884
Max Act: 6.9509. Min Act: -0.1700
Data Index: 3673936 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3884. Min Range: -7.3884
Max Act: 6.8571. Min Act: -0.1700
Data Index: 3324275 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3884. Min Range: -7.3884
Max Act: 6.8884. Min Act: -0.1700
Data Index: 5647346 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3884. Min Range: -7.3884
Max Act: 6.8884. Min Act: -0.1700
Data Index: 121863 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3884. Min Range: -7.3884
Max Act: 6.8571. Min Act: -0.1700
Data Index: 6754715 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19