Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.7387. Min Act: -0.1700
Data Index: 8144743 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.5944. Min Act: -0.1700
Data Index: 6416189 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.6105. Min Act: -0.1700
Data Index: 1275128 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.5783. Min Act: -0.1700
Data Index: 6285155 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.5460. Min Act: -0.1700
Data Index: 428972 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.5299. Min Act: -0.1700
Data Index: 1275132 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4975. Min Act: -0.1700
Data Index: 3988612 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4650. Min Act: -0.1700
Data Index: 8144745 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4975. Min Act: -0.1700
Data Index: 4207589 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4813. Min Act: -0.1700
Data Index: 7795945 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4975. Min Act: -0.1700
Data Index: 1822851 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4813. Min Act: -0.1700
Data Index: 8054731 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4488. Min Act: -0.1700
Data Index: 1927688 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4650. Min Act: -0.1699
Data Index: 4697528 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4488. Min Act: -0.1700
Data Index: 1886612 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4325. Min Act: -0.1700
Data Index: 1696247 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4162. Min Act: -0.1700
Data Index: 1380383 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4325. Min Act: -0.1700
Data Index: 487268 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4488. Min Act: -0.1700
Data Index: 1171871 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7387. Min Range: -2.7387
Max Act: 2.4325. Min Act: -0.1700
Data Index: 5320311 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19