Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1401 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0812. Min Range: -7.0812
Max Act: 7.0812. Min Act: -0.1700
Data Index: 6452937 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0812. Min Range: -7.0812
Max Act: 7.0187. Min Act: -0.1700
Data Index: 198791 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.7999. Min Act: -0.1700
Data Index: 7474885 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.7687. Min Act: -0.1700
Data Index: 2956889 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.6749. Min Act: -0.1700
Data Index: 929667 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.6124. Min Act: -0.1700
Data Index: 4026390 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.6124. Min Act: -0.1700
Data Index: 4957213 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.5499. Min Act: -0.1700
Data Index: 4897654 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.5812. Min Act: -0.1700
Data Index: 3080343 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.5187. Min Act: -0.1700
Data Index: 3847218 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.4874. Min Act: -0.1700
Data Index: 7831045 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.4874. Min Act: -0.1700
Data Index: 3358438 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.4874. Min Act: -0.1700
Data Index: 3878105 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.4874. Min Act: -0.1700
Data Index: 98898 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.4562. Min Act: -0.1700
Data Index: 4949126 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.4562. Min Act: -0.1700
Data Index: 3471363 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.4249. Min Act: -0.1700
Data Index: 1726791 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.4249. Min Act: -0.1700
Data Index: 5890555 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.4249. Min Act: -0.1700
Data Index: 2256486 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0812. Min Range: -7.0812
Max Act: 6.4249. Min Act: -0.1700
Data Index: 5813432 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19