Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2426 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.0470. Min Range: -10.0470
Max Act: 10.0470. Min Act: -0.1700
Data Index: 8400315 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.9845. Min Act: -0.1700
Data Index: 2732757 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.9220. Min Act: -0.1700
Data Index: 4004518 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.7970. Min Act: -0.1700
Data Index: 8098249 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.7970. Min Act: -0.1700
Data Index: 2683492 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.7970. Min Act: -0.1700
Data Index: 5733853 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.7970. Min Act: -0.1700
Data Index: 6902481 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.6720. Min Act: -0.1700
Data Index: 7485935 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.6720. Min Act: -0.1700
Data Index: 3870348 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.6720. Min Act: -0.1700
Data Index: 6950300 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.6095. Min Act: -0.1700
Data Index: 3563367 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.6095. Min Act: -0.1700
Data Index: 7072294 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.6095. Min Act: -0.1700
Data Index: 4021726 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.6720. Min Act: -0.1700
Data Index: 2456915 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.5470. Min Act: -0.1700
Data Index: 4165730 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.5470. Min Act: -0.1700
Data Index: 6825446 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.5470. Min Act: -0.1700
Data Index: 3395482 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.5470. Min Act: -0.1700
Data Index: 6007327 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.5470. Min Act: -0.1700
Data Index: 5070480 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0470. Min Range: -10.0470
Max Act: 9.5470. Min Act: -0.1700
Data Index: 632141 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19