Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5195 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.9654. Min Act: -0.1700
Data Index: 6201139 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.9342. Min Act: -0.1700
Data Index: 3711913 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.9029. Min Act: -0.1700
Data Index: 6575164 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.8717. Min Act: -0.1700
Data Index: 2314102 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.8717. Min Act: -0.1700
Data Index: 2681056 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.8717. Min Act: -0.1700
Data Index: 7894232 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.8092. Min Act: -0.1700
Data Index: 6570875 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.7467. Min Act: -0.1700
Data Index: 5157255 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.7154. Min Act: -0.1700
Data Index: 2833266 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.6842. Min Act: -0.1700
Data Index: 4979384 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.6842. Min Act: -0.1700
Data Index: 8603870 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.6842. Min Act: -0.1700
Data Index: 8177427 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.6529. Min Act: -0.1700
Data Index: 7559652 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.6529. Min Act: -0.1700
Data Index: 1019065 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.6217. Min Act: -0.1700
Data Index: 1780572 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.6217. Min Act: -0.1700
Data Index: 2391378 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.5904. Min Act: -0.1700
Data Index: 1016429 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.6217. Min Act: -0.1700
Data Index: 7409408 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.5904. Min Act: -0.1700
Data Index: 885260 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9654. Min Range: -4.9654
Max Act: 4.5904. Min Act: -0.1700
Data Index: 7024626 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19