Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1495 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2080. Min Range: -9.2080
Max Act: 9.2080. Min Act: -0.1700
Data Index: 7897055 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2080. Min Range: -9.2080
Max Act: 9.0205. Min Act: -0.1700
Data Index: 7853655 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.9580. Min Act: -0.1700
Data Index: 8424273 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.9580. Min Act: -0.1700
Data Index: 8381284 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.8330. Min Act: -0.1700
Data Index: 6683625 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.7080. Min Act: -0.1700
Data Index: 8214997 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.7705. Min Act: -0.1700
Data Index: 6030939 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.7705. Min Act: -0.1700
Data Index: 8660462 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.7705. Min Act: -0.1700
Data Index: 367253 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.7080. Min Act: -0.1700
Data Index: 1734187 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.7080. Min Act: -0.1700
Data Index: 6931875 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.7080. Min Act: -0.1700
Data Index: 1194955 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.6455. Min Act: -0.1700
Data Index: 8170849 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.5830. Min Act: -0.1700
Data Index: 6037846 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.6455. Min Act: -0.1700
Data Index: 133174 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.6455. Min Act: -0.1700
Data Index: 3044126 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.5830. Min Act: -0.1700
Data Index: 6179178 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.5830. Min Act: -0.1700
Data Index: 8403410 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.5205. Min Act: -0.1700
Data Index: 2569350 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2080. Min Range: -9.2080
Max Act: 8.5830. Min Act: -0.1700
Data Index: 4188566 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19