Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5899 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.5038. Min Act: -0.1700
Data Index: 7575486 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.3475. Min Act: -0.1700
Data Index: 410590 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.3163. Min Act: -0.1700
Data Index: 6575462 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.2850. Min Act: -0.1700
Data Index: 3419953 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.2850. Min Act: -0.1700
Data Index: 5445205 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.2225. Min Act: -0.1700
Data Index: 3143636 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.2225. Min Act: -0.1700
Data Index: 6101697 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1913. Min Act: -0.1700
Data Index: 3344451 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.2538. Min Act: -0.1700
Data Index: 5728178 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1913. Min Act: -0.1700
Data Index: 95295 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1913. Min Act: -0.1700
Data Index: 3187569 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1913. Min Act: -0.1700
Data Index: 4035566 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1600. Min Act: -0.1700
Data Index: 3967834 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1288. Min Act: -0.1700
Data Index: 7406698 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1288. Min Act: -0.1700
Data Index: 2734172 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1288. Min Act: -0.1700
Data Index: 6106961 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1288. Min Act: -0.1700
Data Index: 1552201 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.0663. Min Act: -0.1700
Data Index: 1378999 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.1288. Min Act: -0.1700
Data Index: 4376006 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5038. Min Range: -6.5038
Max Act: 6.0975. Min Act: -0.1700
Data Index: 2271740 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19