Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.3529. Min Act: -0.1700
Data Index: 3688517 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.3529. Min Act: -0.1700
Data Index: 1317178 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.2904. Min Act: -0.1700
Data Index: 7803311 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.2591. Min Act: -0.1700
Data Index: 8819511 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.2591. Min Act: -0.1700
Data Index: 1977549 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.2279. Min Act: -0.1700
Data Index: 7146509 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.2279. Min Act: -0.1700
Data Index: 1784297 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.2279. Min Act: -0.1700
Data Index: 330906 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.2279. Min Act: -0.1700
Data Index: 1058949 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1966. Min Act: -0.1700
Data Index: 4031947 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1654. Min Act: -0.1700
Data Index: 8395747 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1966. Min Act: -0.1700
Data Index: 5732860 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1654. Min Act: -0.1700
Data Index: 3537511 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1341. Min Act: -0.1700
Data Index: 6427853 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1654. Min Act: -0.1700
Data Index: 7889299 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1966. Min Act: -0.1700
Data Index: 6572734 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1654. Min Act: -0.1700
Data Index: 8503797 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1341. Min Act: -0.1700
Data Index: 2478741 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1341. Min Act: -0.1700
Data Index: 4995131 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3529. Min Range: -5.3529
Max Act: 5.1654. Min Act: -0.1700
Data Index: 8817803 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19