Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2017 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3859. Min Range: -7.3859
Max Act: 7.3859. Min Act: -0.1700
Data Index: 3640891 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3859. Min Range: -7.3859
Max Act: 7.1672. Min Act: -0.1700
Data Index: 5146428 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3859. Min Range: -7.3859
Max Act: 7.0422. Min Act: -0.1700
Data Index: 6992122 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.9797. Min Act: -0.1700
Data Index: 4078259 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3859. Min Range: -7.3859
Max Act: 7.0109. Min Act: -0.1700
Data Index: 1180209 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.9797. Min Act: -0.1700
Data Index: 3515250 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.9172. Min Act: -0.1700
Data Index: 3932169 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.8234. Min Act: -0.1700
Data Index: 8059169 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.8547. Min Act: -0.1700
Data Index: 6992541 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.8547. Min Act: -0.1700
Data Index: 5905108 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.8234. Min Act: -0.1700
Data Index: 1834878 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.8234. Min Act: -0.1700
Data Index: 731485 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.7922. Min Act: -0.1700
Data Index: 6008772 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.7922. Min Act: -0.1700
Data Index: 4432924 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.7609. Min Act: -0.1700
Data Index: 589143 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.7922. Min Act: -0.1700
Data Index: 3915560 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.7297. Min Act: -0.1700
Data Index: 368901 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.6984. Min Act: -0.1700
Data Index: 2977145 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.6672. Min Act: -0.1700
Data Index: 4745104 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3859. Min Range: -7.3859
Max Act: 6.6984. Min Act: -0.1700
Data Index: 6260766 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19