Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4382 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0771. Min Range: -5.0771
Max Act: 5.0771. Min Act: -0.1700
Data Index: 2990398 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0771. Min Range: -5.0771
Max Act: 5.0146. Min Act: -0.1700
Data Index: 3113342 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.9521. Min Act: -0.1700
Data Index: 4192923 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.9208. Min Act: -0.1700
Data Index: 5732165 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.9208. Min Act: -0.1700
Data Index: 6040177 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.9208. Min Act: -0.1700
Data Index: 8415508 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.8896. Min Act: -0.1700
Data Index: 6965710 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.7958. Min Act: -0.1700
Data Index: 923866 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.8271. Min Act: -0.1700
Data Index: 234538 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.7646. Min Act: -0.1700
Data Index: 2777100 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.7333. Min Act: -0.1700
Data Index: 4257292 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.7646. Min Act: -0.1700
Data Index: 7367765 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.7646. Min Act: -0.1700
Data Index: 6493151 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.7646. Min Act: -0.1700
Data Index: 3294128 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.7646. Min Act: -0.1700
Data Index: 7257408 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.7646. Min Act: -0.1700
Data Index: 6869243 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.7333. Min Act: -0.1700
Data Index: 7489278 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.7333. Min Act: -0.1700
Data Index: 8708634 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.7646. Min Act: -0.1700
Data Index: 5051145 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0771. Min Range: -5.0771
Max Act: 4.7021. Min Act: -0.1700
Data Index: 4954275 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19