Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.8984. Min Act: -0.1700
Data Index: 2450711 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.8359. Min Act: -0.1700
Data Index: 7722396 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.7734. Min Act: -0.1700
Data Index: 8552798 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.6171. Min Act: -0.1700
Data Index: 7202901 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.6171. Min Act: -0.1700
Data Index: 8310423 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.5859. Min Act: -0.1700
Data Index: 3366565 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.4609. Min Act: -0.1700
Data Index: 6147316 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.3984. Min Act: -0.1700
Data Index: 7820024 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.3984. Min Act: -0.1700
Data Index: 5803345 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.3046. Min Act: -0.1700
Data Index: 8131518 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.3046. Min Act: -0.1700
Data Index: 3516688 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.3046. Min Act: -0.1700
Data Index: 5218880 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.3046. Min Act: -0.1700
Data Index: 6980103 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.3046. Min Act: -0.1700
Data Index: 4995536 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.2734. Min Act: -0.1700
Data Index: 5236904 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.2734. Min Act: -0.1700
Data Index: 7477223 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.2734. Min Act: -0.1700
Data Index: 4092902 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.2734. Min Act: -0.1700
Data Index: 1385960 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.2734. Min Act: -0.1700
Data Index: 2995035 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8984. Min Range: -6.8984
Max Act: 6.2734. Min Act: -0.1700
Data Index: 7171684 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19