Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3191 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4750. Min Range: -4.4750
Max Act: 4.4750. Min Act: -0.1700
Data Index: 7456991 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4750. Min Range: -4.4750
Max Act: 4.4125. Min Act: -0.1700
Data Index: 7097440 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4750. Min Range: -4.4750
Max Act: 4.2250. Min Act: -0.1700
Data Index: 3992764 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4750. Min Range: -4.4750
Max Act: 4.1312. Min Act: -0.1700
Data Index: 6958163 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4750. Min Range: -4.4750
Max Act: 4.0687. Min Act: -0.1700
Data Index: 5273072 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4750. Min Range: -4.4750
Max Act: 4.0375. Min Act: -0.1700
Data Index: 331112 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.9749. Min Act: -0.1700
Data Index: 3636661 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.8811. Min Act: -0.1700
Data Index: 1567120 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.8811. Min Act: -0.1700
Data Index: 4807408 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.8811. Min Act: -0.1700
Data Index: 2388194 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.8811. Min Act: -0.1700
Data Index: 3386754 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.9124. Min Act: -0.1700
Data Index: 5470901 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.8499. Min Act: -0.1700
Data Index: 7190198 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.8499. Min Act: -0.1700
Data Index: 3992761 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.8499. Min Act: -0.1700
Data Index: 4762092 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.8186. Min Act: -0.1700
Data Index: 4739519 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.7873. Min Act: -0.1700
Data Index: 1128073 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.7717. Min Act: -0.1700
Data Index: 5275909 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.7873. Min Act: -0.1700
Data Index: 6284783 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4750. Min Range: -4.4750
Max Act: 3.7873. Min Act: -0.1700
Data Index: 7300792 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19