Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3906 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0769. Min Range: -7.0769
Max Act: 7.0769. Min Act: -0.1700
Data Index: 5011738 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.9831. Min Act: -0.1700
Data Index: 4805530 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0769. Min Range: -7.0769
Max Act: 7.0144. Min Act: -0.1700
Data Index: 6178543 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0769. Min Range: -7.0769
Max Act: 7.0144. Min Act: -0.1700
Data Index: 6521383 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.9519. Min Act: -0.1700
Data Index: 2886315 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.9206. Min Act: -0.1700
Data Index: 8777089 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.9206. Min Act: -0.1700
Data Index: 5411027 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.8894. Min Act: -0.1700
Data Index: 7683204 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.8894. Min Act: -0.1700
Data Index: 4615186 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.8894. Min Act: -0.1700
Data Index: 2826751 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.8894. Min Act: -0.1700
Data Index: 741033 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.8894. Min Act: -0.1700
Data Index: 3118273 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.8894. Min Act: -0.1700
Data Index: 1227437 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.8581. Min Act: -0.1700
Data Index: 7144317 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.8581. Min Act: -0.1700
Data Index: 968303 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.8269. Min Act: -0.1700
Data Index: 1225469 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.7956. Min Act: -0.1700
Data Index: 277506 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.7956. Min Act: -0.1700
Data Index: 4176553 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.7956. Min Act: -0.1700
Data Index: 8047572 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0769. Min Range: -7.0769
Max Act: 6.7956. Min Act: -0.1700
Data Index: 6376847 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19