Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 672 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1237. Min Range: -8.1237
Max Act: 8.1237. Min Act: -0.1700
Data Index: 425401 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1237. Min Range: -8.1237
Max Act: 8.1237. Min Act: -0.1700
Data Index: 7501761 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.9987. Min Act: -0.1700
Data Index: 4429201 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.9362. Min Act: -0.1700
Data Index: 1507366 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.8737. Min Act: -0.1700
Data Index: 288938 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.8112. Min Act: -0.1700
Data Index: 3908054 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.7799. Min Act: -0.1700
Data Index: 3294140 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.7799. Min Act: -0.1700
Data Index: 6201211 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.7174. Min Act: -0.1700
Data Index: 425402 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.6549. Min Act: -0.1700
Data Index: 5824834 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.7174. Min Act: -0.1700
Data Index: 8753231 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.6862. Min Act: -0.1700
Data Index: 3532481 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.6549. Min Act: -0.1700
Data Index: 7153110 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.6862. Min Act: -0.1700
Data Index: 2389235 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.6237. Min Act: -0.1700
Data Index: 109859 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.6549. Min Act: -0.1700
Data Index: 1756423 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.6549. Min Act: -0.1700
Data Index: 1462945 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.6237. Min Act: -0.1700
Data Index: 1557031 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.6549. Min Act: -0.1700
Data Index: 3839013 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1237. Min Range: -8.1237
Max Act: 7.6237. Min Act: -0.1700
Data Index: 2466130 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19