Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3077 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.8475. Min Act: -0.1700
Data Index: 4877144 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.7850. Min Act: -0.1700
Data Index: 7568627 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.6912. Min Act: -0.1700
Data Index: 7339854 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.6287. Min Act: -0.1700
Data Index: 1236172 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.5662. Min Act: -0.1700
Data Index: 7181957 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.5350. Min Act: -0.1700
Data Index: 5050370 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.4412. Min Act: -0.1700
Data Index: 3423892 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.4100. Min Act: -0.1700
Data Index: 5000727 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.4100. Min Act: -0.1700
Data Index: 4008069 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.4100. Min Act: -0.1700
Data Index: 4434610 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.3787. Min Act: -0.1700
Data Index: 7339853 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.3475. Min Act: -0.1700
Data Index: 6478966 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.3475. Min Act: -0.1700
Data Index: 7845790 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.3475. Min Act: -0.1700
Data Index: 8544297 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.3475. Min Act: -0.1700
Data Index: 1827978 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.3475. Min Act: -0.1700
Data Index: 1437791 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.3162. Min Act: -0.1700
Data Index: 5456999 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.3162. Min Act: -0.1700
Data Index: 2621865 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.2850. Min Act: -0.1700
Data Index: 11820 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8475. Min Range: -7.8475
Max Act: 7.2225. Min Act: -0.1700
Data Index: 1313956 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19