Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2111 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.2778. Min Act: -0.1700
Data Index: 3548228 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.2153. Min Act: -0.1700
Data Index: 1012251 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.0903. Min Act: -0.1700
Data Index: 8293448 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.0903. Min Act: -0.1700
Data Index: 5417793 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.0278. Min Act: -0.1700
Data Index: 129399 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.0278. Min Act: -0.1700
Data Index: 7342400 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9965. Min Act: -0.1700
Data Index: 2886946 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9653. Min Act: -0.1700
Data Index: 7303230 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9965. Min Act: -0.1700
Data Index: 4626959 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9340. Min Act: -0.1700
Data Index: 5596903 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9965. Min Act: -0.1700
Data Index: 3091731 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9653. Min Act: -0.1700
Data Index: 3321868 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9653. Min Act: -0.1700
Data Index: 78593 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9340. Min Act: -0.1700
Data Index: 4286880 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9028. Min Act: -0.1700
Data Index: 7668637 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9028. Min Act: -0.1700
Data Index: 113806 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.8403. Min Act: -0.1700
Data Index: 4869265 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9028. Min Act: -0.1700
Data Index: 5135276 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.8403. Min Act: -0.1700
Data Index: 93627 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.8715. Min Act: -0.1700
Data Index: 8307910 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19