Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4973 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0159. Min Range: -4.0159
Max Act: 4.0159. Min Act: -0.1700
Data Index: 8829155 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.8283. Min Act: -0.1700
Data Index: 773512 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.6719. Min Act: -0.1700
Data Index: 6927953 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.6406. Min Act: -0.1700
Data Index: 2368506 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.6406. Min Act: -0.1700
Data Index: 635718 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.6093. Min Act: -0.1700
Data Index: 1829132 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.6093. Min Act: -0.1700
Data Index: 5144774 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.5780. Min Act: -0.1700
Data Index: 3220855 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.5780. Min Act: -0.1700
Data Index: 8563352 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.5937. Min Act: -0.1700
Data Index: 6804029 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.5624. Min Act: -0.1700
Data Index: 6708568 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.5624. Min Act: -0.1700
Data Index: 7791460 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.5624. Min Act: -0.1700
Data Index: 3400013 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.5624. Min Act: -0.1700
Data Index: 633109 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.5624. Min Act: -0.1700
Data Index: 7649143 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.5311. Min Act: -0.1700
Data Index: 3972549 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.5311. Min Act: -0.1700
Data Index: 8103783 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.5154. Min Act: -0.1700
Data Index: 6158068 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.4997. Min Act: -0.1700
Data Index: 4950050 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.5311. Min Act: -0.1700
Data Index: 6368071 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19