Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2346 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.6340. Min Act: -0.1700
Data Index: 1611001 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.4153. Min Act: -0.1700
Data Index: 6547083 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.3840. Min Act: -0.1700
Data Index: 7523192 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.3528. Min Act: -0.1700
Data Index: 7805451 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.3528. Min Act: -0.1700
Data Index: 4823493 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.2590. Min Act: -0.1700
Data Index: 164306 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.1653. Min Act: -0.1700
Data Index: 1763957 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.2278. Min Act: -0.1700
Data Index: 1566981 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.1340. Min Act: -0.1700
Data Index: 1763955 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.1653. Min Act: -0.1700
Data Index: 1763958 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.1653. Min Act: -0.1700
Data Index: 4554787 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.1028. Min Act: -0.1700
Data Index: 1058910 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.0715. Min Act: -0.1700
Data Index: 3690116 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.0715. Min Act: -0.1700
Data Index: 556417 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.0715. Min Act: -0.1700
Data Index: 1843511 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.0403. Min Act: -0.1700
Data Index: 2981486 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.0403. Min Act: -0.1700
Data Index: 3561174 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.0090. Min Act: -0.1700
Data Index: 8218442 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6340. Min Range: -7.6340
Max Act: 7.0090. Min Act: -0.1700
Data Index: 4116140 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6340. Min Range: -7.6340
Max Act: 6.9778. Min Act: -0.1700
Data Index: 5508833 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19