Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 305 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.4370. Min Act: -0.1700
Data Index: 1126177 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.3900. Min Act: -0.1700
Data Index: 1421587 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.3586. Min Act: -0.1700
Data Index: 6664125 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.3586. Min Act: -0.1700
Data Index: 1045988 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.3430. Min Act: -0.1700
Data Index: 3386847 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.3273. Min Act: -0.1700
Data Index: 5078529 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.2959. Min Act: -0.1700
Data Index: 4836128 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.3273. Min Act: -0.1700
Data Index: 5974814 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.2959. Min Act: -0.1700
Data Index: 7794480 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.2645. Min Act: -0.1700
Data Index: 3008460 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.2645. Min Act: -0.1700
Data Index: 3601883 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.2330. Min Act: -0.1700
Data Index: 1310046 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.2330. Min Act: -0.1700
Data Index: 8682435 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.1859. Min Act: -0.1700
Data Index: 1681912 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.1859. Min Act: -0.1700
Data Index: 1475081 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.2016. Min Act: -0.1700
Data Index: 4266489 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.1701. Min Act: -0.1700
Data Index: 1615309 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.1859. Min Act: -0.1700
Data Index: 2408589 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.1701. Min Act: -0.1700
Data Index: 2833552 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4370. Min Range: -3.4370
Max Act: 3.1544. Min Act: -0.1700
Data Index: 7932309 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19