Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 303 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.5208. Min Act: -0.1700
Data Index: 460803 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.4896. Min Act: -0.1700
Data Index: 4845828 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.4271. Min Act: -0.1700
Data Index: 3785211 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.4271. Min Act: -0.1700
Data Index: 2616827 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.4583. Min Act: -0.1700
Data Index: 2540568 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.4271. Min Act: -0.1700
Data Index: 276534 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.3958. Min Act: -0.1700
Data Index: 8518003 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.3333. Min Act: -0.1700
Data Index: 4395353 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.3646. Min Act: -0.1700
Data Index: 4881671 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.3333. Min Act: -0.1700
Data Index: 8253644 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.3333. Min Act: -0.1700
Data Index: 5168815 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.3021. Min Act: -0.1700
Data Index: 1079515 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.2708. Min Act: -0.1700
Data Index: 8016017 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.2396. Min Act: -0.1700
Data Index: 6683972 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.2708. Min Act: -0.1700
Data Index: 6529507 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.2083. Min Act: -0.1700
Data Index: 1990735 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.2083. Min Act: -0.1700
Data Index: 747655 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.1771. Min Act: -0.1700
Data Index: 1338111 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.2083. Min Act: -0.1700
Data Index: 1563685 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5208. Min Range: -4.5208
Max Act: 4.2083. Min Act: -0.1700
Data Index: 8222632 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19