Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1854 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.3556. Min Act: -0.1700
Data Index: 7779146 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.3720. Min Act: -0.1700
Data Index: 5510759 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.3064. Min Act: -0.1700
Data Index: 2481019 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.3064. Min Act: -0.1700
Data Index: 847701 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2735. Min Act: -0.1700
Data Index: 883710 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2570. Min Act: -0.1700
Data Index: 2924586 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2570. Min Act: -0.1700
Data Index: 6882092 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2405. Min Act: -0.1700
Data Index: 6469306 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2570. Min Act: -0.1700
Data Index: 3305711 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2405. Min Act: -0.1700
Data Index: 7154046 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2073. Min Act: -0.1700
Data Index: 667201 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2405. Min Act: -0.1700
Data Index: 8379138 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2405. Min Act: -0.1700
Data Index: 1741675 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2405. Min Act: -0.1700
Data Index: 194938 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2570. Min Act: -0.1700
Data Index: 7952905 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2239. Min Act: -0.1700
Data Index: 7673139 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2405. Min Act: -0.1700
Data Index: 1213321 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2239. Min Act: -0.1700
Data Index: 1085292 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2239. Min Act: -0.1700
Data Index: 8183960 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3720. Min Range: -2.3720
Max Act: 2.2239. Min Act: -0.1700
Data Index: 2990845 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19