Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2656. Min Range: -5.2656
Max Act: 5.2656. Min Act: -0.1700
Data Index: 5747232 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2656. Min Range: -5.2656
Max Act: 5.0781. Min Act: -0.1700
Data Index: 3572082 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2656. Min Range: -5.2656
Max Act: 5.0156. Min Act: -0.1700
Data Index: 413724 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2656. Min Range: -5.2656
Max Act: 5.0156. Min Act: -0.1700
Data Index: 7182301 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.9531. Min Act: -0.1700
Data Index: 8769756 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.9531. Min Act: -0.1700
Data Index: 6761545 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.9219. Min Act: -0.1700
Data Index: 2533745 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.8906. Min Act: -0.1700
Data Index: 2814267 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.9219. Min Act: -0.1700
Data Index: 5225788 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.8906. Min Act: -0.1700
Data Index: 4442584 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.9219. Min Act: -0.1700
Data Index: 6144733 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.8906. Min Act: -0.1700
Data Index: 1965782 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.8594. Min Act: -0.1700
Data Index: 8765133 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.7969. Min Act: -0.1700
Data Index: 4483826 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.8281. Min Act: -0.1700
Data Index: 1172117 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.7969. Min Act: -0.1700
Data Index: 8239885 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.8281. Min Act: -0.1700
Data Index: 2137661 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.8281. Min Act: -0.1700
Data Index: 734169 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.8281. Min Act: -0.1700
Data Index: 1323211 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2656. Min Range: -5.2656
Max Act: 4.8281. Min Act: -0.1700
Data Index: 1829824 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19