Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 800 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.4182. Min Act: -0.1700
Data Index: 4094398 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.2307. Min Act: -0.1700
Data Index: 1118211 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.2619. Min Act: -0.1700
Data Index: 5933841 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.2307. Min Act: -0.1700
Data Index: 6065597 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.2619. Min Act: -0.1700
Data Index: 7107239 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.2307. Min Act: -0.1700
Data Index: 3408361 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.2307. Min Act: -0.1700
Data Index: 6331136 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.1994. Min Act: -0.1700
Data Index: 4001831 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.1369. Min Act: -0.1700
Data Index: 6786714 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.1369. Min Act: -0.1700
Data Index: 215476 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.1057. Min Act: -0.1700
Data Index: 1799578 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0744. Min Act: -0.1700
Data Index: 784595 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0744. Min Act: -0.1700
Data Index: 7626820 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0744. Min Act: -0.1700
Data Index: 1935190 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0432. Min Act: -0.1700
Data Index: 3797130 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0432. Min Act: -0.1700
Data Index: 2226408 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0432. Min Act: -0.1700
Data Index: 2285700 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0119. Min Act: -0.1700
Data Index: 101737 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0119. Min Act: -0.1700
Data Index: 3344484 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4182. Min Range: -5.4182
Max Act: 5.0119. Min Act: -0.1700
Data Index: 2459440 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19