Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1540 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.9173. Min Act: -0.1700
Data Index: 2615135 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.9173. Min Act: -0.1700
Data Index: 4789 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.8548. Min Act: -0.1700
Data Index: 7156731 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.8860. Min Act: -0.1700
Data Index: 8391824 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.8235. Min Act: -0.1700
Data Index: 3725 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.8235. Min Act: -0.1700
Data Index: 5832820 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.7609. Min Act: -0.1700
Data Index: 8005063 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.7922. Min Act: -0.1700
Data Index: 2350711 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.7922. Min Act: -0.1700
Data Index: 22752 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.7922. Min Act: -0.1700
Data Index: 5304596 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.7609. Min Act: -0.1700
Data Index: 1176539 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.7297. Min Act: -0.1700
Data Index: 5856076 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.7297. Min Act: -0.1700
Data Index: 5361997 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.7609. Min Act: -0.1700
Data Index: 3212461 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.7609. Min Act: -0.1700
Data Index: 1354080 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.7609. Min Act: -0.1700
Data Index: 4040066 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.6984. Min Act: -0.1700
Data Index: 1035314 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.7297. Min Act: -0.1700
Data Index: 6074294 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.7297. Min Act: -0.1700
Data Index: 2566709 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9173. Min Range: -3.9173
Max Act: 3.7297. Min Act: -0.1700
Data Index: 2595442 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19