Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0379. Min Range: -3.0379
Max Act: 3.0379. Min Act: -0.1700
Data Index: 3655581 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0379. Min Range: -3.0379
Max Act: 3.0222. Min Act: -0.1700
Data Index: 7041184 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8956. Min Act: -0.1700
Data Index: 6748339 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8797. Min Act: -0.1700
Data Index: 5652991 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8956. Min Act: -0.1700
Data Index: 5345325 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8797. Min Act: -0.1700
Data Index: 7644899 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8638. Min Act: -0.1700
Data Index: 5660183 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8320. Min Act: -0.1700
Data Index: 7300279 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8320. Min Act: -0.1700
Data Index: 5268185 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8161. Min Act: -0.1700
Data Index: 5819872 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8161. Min Act: -0.1700
Data Index: 7547707 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8320. Min Act: -0.1700
Data Index: 1146979 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8161. Min Act: -0.1700
Data Index: 7809337 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8002. Min Act: -0.1700
Data Index: 8220980 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8002. Min Act: -0.1700
Data Index: 3295809 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8002. Min Act: -0.1700
Data Index: 1431357 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.7843. Min Act: -0.1700
Data Index: 1241330 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.8002. Min Act: -0.1700
Data Index: 5952544 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.7843. Min Act: -0.1700
Data Index: 6672499 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0379. Min Range: -3.0379
Max Act: 2.7843. Min Act: -0.1700
Data Index: 6777736 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19