Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5732 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.3053. Min Act: -0.1700
Data Index: 2595966 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.2740. Min Act: -0.1700
Data Index: 5483362 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1803. Min Act: -0.1700
Data Index: 2665200 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.2115. Min Act: -0.1700
Data Index: 5801864 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1803. Min Act: -0.1700
Data Index: 1422082 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1803. Min Act: -0.1700
Data Index: 1282035 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1490. Min Act: -0.1700
Data Index: 8189461 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1490. Min Act: -0.1700
Data Index: 5887950 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1490. Min Act: -0.1700
Data Index: 7498253 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1490. Min Act: -0.1700
Data Index: 2238546 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1490. Min Act: -0.1700
Data Index: 4483050 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1490. Min Act: -0.1700
Data Index: 1018794 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0865. Min Act: -0.1700
Data Index: 4156415 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0865. Min Act: -0.1700
Data Index: 8104333 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0865. Min Act: -0.1700
Data Index: 1040878 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0865. Min Act: -0.1700
Data Index: 1945605 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0865. Min Act: -0.1700
Data Index: 2107188 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0553. Min Act: -0.1700
Data Index: 7212670 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0240. Min Act: -0.1700
Data Index: 6531151 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0553. Min Act: -0.1700
Data Index: 6066143 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19