Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1894 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0601. Min Range: -6.0601
Max Act: 6.0601. Min Act: -0.1700
Data Index: 3445667 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.9976. Min Act: -0.1700
Data Index: 5547261 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.9663. Min Act: -0.1700
Data Index: 8050020 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.9976. Min Act: -0.1700
Data Index: 8108284 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.9663. Min Act: -0.1700
Data Index: 2215474 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.9038. Min Act: -0.1700
Data Index: 5420313 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.8413. Min Act: -0.1700
Data Index: 7510684 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.8413. Min Act: -0.1700
Data Index: 3523296 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.8413. Min Act: -0.1700
Data Index: 7105526 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.8413. Min Act: -0.1700
Data Index: 7148804 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.8413. Min Act: -0.1700
Data Index: 6930133 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.8413. Min Act: -0.1700
Data Index: 5249330 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.8101. Min Act: -0.1700
Data Index: 8695265 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.7788. Min Act: -0.1700
Data Index: 6343457 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.7788. Min Act: -0.1700
Data Index: 1935155 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.7788. Min Act: -0.1700
Data Index: 2081756 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.7476. Min Act: -0.1700
Data Index: 787724 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.7476. Min Act: -0.1700
Data Index: 899120 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.7476. Min Act: -0.1700
Data Index: 5725327 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.7163. Min Act: -0.1700
Data Index: 2160200 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19