Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1187. Min Range: -6.1187
Max Act: 6.1187. Min Act: -0.1700
Data Index: 5972597 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1187. Min Range: -6.1187
Max Act: 6.0562. Min Act: -0.1700
Data Index: 6457413 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1187. Min Range: -6.1187
Max Act: 6.0250. Min Act: -0.1700
Data Index: 139392 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1187. Min Range: -6.1187
Max Act: 6.0562. Min Act: -0.1700
Data Index: 1328105 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1187. Min Range: -6.1187
Max Act: 6.0250. Min Act: -0.1700
Data Index: 6606860 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.9625. Min Act: -0.1700
Data Index: 5521264 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.9937. Min Act: -0.1700
Data Index: 3144119 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.9937. Min Act: -0.1700
Data Index: 3106904 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.9625. Min Act: -0.1700
Data Index: 8127231 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.8687. Min Act: -0.1700
Data Index: 1328109 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.8687. Min Act: -0.1700
Data Index: 3827867 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.8375. Min Act: -0.1700
Data Index: 7701416 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.8375. Min Act: -0.1700
Data Index: 4671391 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.8062. Min Act: -0.1700
Data Index: 6606856 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.7750. Min Act: -0.1700
Data Index: 7532813 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.7750. Min Act: -0.1700
Data Index: 6939731 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.7750. Min Act: -0.1700
Data Index: 5412915 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.7750. Min Act: -0.1700
Data Index: 7340169 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.7437. Min Act: -0.1700
Data Index: 7969949 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1187. Min Range: -6.1187
Max Act: 5.7437. Min Act: -0.1700
Data Index: 6048253 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19