Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1022 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.6470. Min Act: -0.1700
Data Index: 1814634 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.5220. Min Act: -0.1700
Data Index: 6608236 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.3970. Min Act: -0.1700
Data Index: 3967631 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.3345. Min Act: -0.1700
Data Index: 6821473 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.2720. Min Act: -0.1700
Data Index: 6821472 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.2095. Min Act: -0.1700
Data Index: 5649189 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.2095. Min Act: -0.1700
Data Index: 5493025 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.1470. Min Act: -0.1700
Data Index: 2124250 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.0220. Min Act: -0.1700
Data Index: 4840563 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.0220. Min Act: -0.1700
Data Index: 2189203 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6470. Min Range: -8.6470
Max Act: 8.0220. Min Act: -0.1700
Data Index: 8668543 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6470. Min Range: -8.6470
Max Act: 7.9595. Min Act: -0.1700
Data Index: 5452178 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6470. Min Range: -8.6470
Max Act: 7.9595. Min Act: -0.1700
Data Index: 6845015 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6470. Min Range: -8.6470
Max Act: 7.9595. Min Act: -0.1700
Data Index: 4450594 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6470. Min Range: -8.6470
Max Act: 7.9595. Min Act: -0.1700
Data Index: 5969534 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6470. Min Range: -8.6470
Max Act: 7.8345. Min Act: -0.1700
Data Index: 1137767 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6470. Min Range: -8.6470
Max Act: 7.8970. Min Act: -0.1700
Data Index: 8553921 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6470. Min Range: -8.6470
Max Act: 7.8970. Min Act: -0.1700
Data Index: 3472036 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6470. Min Range: -8.6470
Max Act: 7.8970. Min Act: -0.1700
Data Index: 785522 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6470. Min Range: -8.6470
Max Act: 7.8970. Min Act: -0.1700
Data Index: 6995502 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19